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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1636
    Prev
    Next
    INDEX
    Explanations

    java code import statements

    oai_token-act-pair · gemini-2.0-flash

    say "the period ."

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    KommentareTeilen
    -0.63
     okuyayım
    -0.57
    $.
    
    -0.57
    ).
    
    -0.56
    drawiam
    -0.54
    )!
    -0.53
     ℃
    -0.52
    popd
    -0.52
    !]
    -0.52
    ".
    
    -0.52
    POSITIVE LOGITS
    ReusableCell
    0.68
    JoinColumn
    0.63
    PickerController
    0.61
    WebVitals
    0.60
    interopRequire
    0.57
    mybatisplus
    0.56
    TProtocol
    0.55
    zzleHttp
    0.55
    protoc
    0.54
    BindView
    0.53
    Activations Density 2.868%

    No Known Activations