© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1895
    Prev
    Next
    INDEX
    Explanations

    proper nouns, acronyms and product/company names

    oai_token-act-pair · gemini-2.0-flash

    car brands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    melho
    -0.51
     saker
    -0.51
    ecker
    -0.49
     nyom
    -0.49
    ỳnh
    -0.48
    ToolStripButton
    -0.48
    localPosition
    -0.47
     tolerancia
    -0.46
    AndroidJUnit
    -0.46
     actuels
    -0.46
    POSITIVE LOGITS
    ритори
    0.78
     itſelf
    0.75
     pleaſure
    0.73
     Houſe
    0.69
     للمعارف
    0.69
     ſche
    0.65
     houſe
    0.64
     متعلقه
    0.64
    MENAFN
    0.63
     greateſt
    0.62
    Activations Density 27.365%

    No Known Activations