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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16227
    Prev
    Next
    INDEX
    Explanations

    sentences where something is being confirmed or proven

    oai_token-act-pair · gemini-2.0-flash

    indeed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     שוליים
    -0.71
     ویکی‌پدیا
    -0.68
    Personendaten
    -0.68
    ArrowToggle
    -0.67
     disambiguazione
    -0.66
    SequentialGroup
    -0.63
    Vidite
    -0.62
    writeField
    -0.62
    HasAnnotation
    -0.61
    帖最后由
    -0.60
    POSITIVE LOGITS
    paque
    0.53
    uese
    0.52
    ENTI
    0.50
    Technik
    0.48
    otyp
    0.48
    ologues
    0.47
    ocie
    0.47
     Trades
    0.47
    COMPR
    0.47
    waren
    0.47
    Activations Density 1.545%

    No Known Activations