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. 14052
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and file paths with extensions like `.h`.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · 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
    .
    -0.77
    ()")
    -0.61
    .~(\
    -0.60
     +=
    -0.60
    .,
    -0.57
    .);
    -0.56
    .),
    -0.55
    цезда
    -0.54
    wnia
    -0.53
    ConfigureAwait
    -0.53
    POSITIVE LOGITS
    Географи
    0.54
     initComponents
    0.52
    IntoConstraints
    0.50
     sebou
    0.49
     ©️
    0.48
    fjspx
    0.47
    ThroughAttribute
    0.47
    OGND
    0.47
     Orrell
    0.47
     Baillargeon
    0.46
    Activations Density 1.982%

    No Known Activations