© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15697
    Prev
    Next
    INDEX
    Explanations

    words related to law, rules, or authority

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    WebElementEntity
    -0.73
     larmes
    -0.73
     credere
    -0.70
     stamens
    -0.70
     demurrer
    -0.69
    GeoNames
    -0.69
     nationaux
    -0.69
     didst
    -0.68
     feroit
    -0.67
     namorado
    -0.67
    POSITIVE LOGITS
    <bos>
    0.81
    JspWriter
    0.69
    +:+
    0.68
     the
    0.66
    UIControlState
    0.65
     arşivlendi
    0.64
    etheless
    0.64
     in
    0.62
    erdings
    0.61
    tagHelperRunner
    0.58
    Activations Density 1.940%

    No Known Activations