© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10941
    Prev
    Next
    INDEX
    Explanations

    a mix of random characters, strings containing measurement units, and ingredients from a Turkish menu

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    djangoproject
    -0.72
    ydd
    -0.60
    ValueStyle
    -0.59
    uttori
    -0.57
    tieg
    -0.55
    Према
    -0.54
    edicated
    -0.54
    geführten
    -0.53
     getFirst
    -0.53
    SEY
    -0.52
    POSITIVE LOGITS
     Candid
    0.50
    ollectionView
    0.49
    PageRoute
    0.47
     Perci
    0.44
    DoubleQuotes
    0.43
     Arka
    0.43
    IsContent
    0.43
    FRC
    0.42
     hort
    0.42
     integral
    0.42
    Activations Density 0.553%

    No Known Activations