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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14113
    Prev
    Next
    INDEX
    Explanations

    software license agreements

    oai_token-act-pair · gemini-2.0-flash

    Software licenses

    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
    tvguidetime
    -0.73
    parsedMessage
    -0.64
    ngrx
    -0.63
     gql
    -0.63
    ChildScrollView
    -0.62
    تقاوى
    -0.62
     فريبيس
    -0.62
     szóci
    -0.61
    autés
    -0.60
     Polls
    -0.60
    POSITIVE LOGITS
     Creative
    0.46
     Aufla
    0.46
    mpl
    0.42
     творчества
    0.41
    تفصیلات
    0.41
    CC
    0.40
    Creative
    0.40
    بیشتر
    0.40
    hydrogenase
    0.40
     compromise
    0.40
    Activations Density 1.259%

    No Known Activations