© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10828
    Prev
    Next
    INDEX
    Explanations

    a mix of words possibly related to: a) Hindu religious practices connected to evening prayers; b) various linguistic and mathematical items like keys; c) medical terms related to cells and oxygen absorption; d) words related to truth or the church, and e) words related to shaving and minty freshness

    oai_token-act-pair · gemini-2.0-flash

    Religion, health, daily life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.63
    lapsingToolbar
    -0.55
     AppCompatTheme
    -0.50
     linkovi
    -0.50
     }{@
    -0.49
    bindingNavigator
    -0.49
    laze
    -0.48
    intellij
    -0.48
    ilderness
    -0.48
    UALA
    -0.48
    POSITIVE LOGITS
    fjspx
    0.54
    DockStyle
    0.52
    AnimationsModule
    0.49
    ربای
    0.48
    DoubleQuotes
    0.48
    \{\\
    0.47
    ləş
    0.47
     themſelves
    0.46
    IsContent
    0.46
     himſelf
    0.46
    Activations Density 2.274%

    No Known Activations