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. 16349
    Prev
    Next
    INDEX
    Explanations

    the beginning of variable declarations such as "var" "const" or "let"

    oai_token-act-pair · gemini-2.0-flash

    Javascript variable declaration

    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
    GraphicsUnit
    -0.44
    Tint
    -0.43
     Folio
    -0.40
     Argo
    -0.40
     ster
    -0.40
    сто
    -0.39
     Sotheby
    -0.39
    DBObject
    -0.39
     Vue
    -0.38
     Pole
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.78
    verwijspagina
    0.69
     للمعارف
    0.69
     nahilalakip
    0.65
    )++;
    0.63
    )}</
    0.63
     صوتيه
    0.61
    AndEndTag
    0.60
     kasarigan
    0.60
     насељу
    0.59
    Activations Density 1.311%

    No Known Activations