© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12216
    Prev
    Next
    INDEX
    Explanations

    tokens that appear to be parts of code or legal citations and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    formik
    -0.68
     {*}
    -0.65
     HasFactory
    -0.65
    ודם
    -0.63
    neſs
    -0.61
     mapStateToProps
    -0.59
     Bok
    -0.59
     stabilisation
    -0.57
    lgari
    -0.56
    figsize
    -0.56
    POSITIVE LOGITS
    <bos>
    0.69
    timbangan
    0.56
    httphttps
    0.50
    kháu
    0.48
     linkovi
    0.46
     متعلقه
    0.45
     expédié
    0.44
     stanovnika
    0.43
     propOrder
    0.43
     dahin
    0.43
    Activations Density 32.914%

    No Known Activations