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. 16276
    Prev
    Next
    INDEX
    Explanations

    C code, specifically definitions, pointers, and structs

    oai_token-act-pair · gemini-2.0-flash

    *

    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
    ⓧ
    -0.57
    cloudflare
    -0.51
     Référence
    -0.47
    saraba
    -0.44
    DebuggerNonUser
    -0.42
     Integer
    -0.42
    étique
    -0.42
    Билгалдахарш
    -0.42
    //</
    -0.42
    häng
    -0.41
    POSITIVE LOGITS
     itſelf
    0.67
     виправивши
    0.63
     ſte
    0.62
     Física
    0.60
     Comte
    0.59
     viſ
    0.58
     depositphotos
    0.57
     myſelf
    0.57
     poffible
    0.56
    manual
    0.55
    Activations Density 0.913%

    No Known Activations