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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14082
    Prev
    Next
    INDEX
    Explanations

    mathematical equations, expressions, and formulas

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    könyv
    -0.52
    LayoutPanel
    -0.52
    Clik
    -0.50
    ViewImports
    -0.48
    prnewswire
    -0.48
     AssemblyCulture
    -0.47
     olympique
    -0.47
     jScrollPane
    -0.47
    binaan
    -0.47
    icide
    -0.47
    POSITIVE LOGITS
     We
    0.62
    --*/
    0.61
    aranja
    0.58
    ftagPool
    0.58
    __*/
    0.58
    interopRequire
    0.58
     \%$\\
    0.58
    ByExample
    0.57
     See
    0.57
    rendo
    0.52
    Activations Density 3.162%

    No Known Activations