Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16308
    Prev
    Next
    INDEX
    Explanations

    technical jargon used in chemistry, software development, and law

    oai_token-act-pair · gemini-2.0-flash

    Policy

    np_token-act-pair-logits · gemini-2.0-flash

    Programming/chemical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.64
     ligiloj
    -0.57
    oa̍t
    -0.57
    UserScript
    -0.52
     ويكيميديا
    -0.51
    __((
    -0.50
     &[
    -0.50
     bunker
    -0.50
    datagrid
    -0.49
    Controllo
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.69
     للاسماء
    0.68
     vulgaires
    0.53
     seguida
    0.51
    LabelTagHelper
    0.49
    mentaux
    0.49
    runs
    0.48
     defaultstate
    0.48
    abestanden
    0.47
    لينكات
    0.47
    Activations Density 3.999%

    No Known Activations