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. 1652
    Prev
    Next
    INDEX
    Explanations

    snippets of computer code, horizontal lines, and words "business"

    oai_token-act-pair · gemini-2.0-flash

    Code/Markup related

    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
    <bos>
    0.16
     herbic
    0.26
     kull
    0.27
    俗
    0.28
     reli
    0.29
     plena
    0.30
    関連記事
    0.30
     carn
    0.30
     aca
    0.30
     perten
    0.30
    POSITIVE LOGITS
    OGND
    1.52
     تضيفلها
    1.41
    RenderAtEndOf
    1.37
     ویکی‌پدیا
    1.35
    bootstrapcdn
    1.32
    webElementXpaths
    1.32
     disambiguazione
    1.29
    MigrationBuilder
    1.27
     typelib
    1.27
    клопе
    1.27
    Activations Density 2.243%

    No Known Activations