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. 16261
    Prev
    Next
    INDEX
    Explanations

    computer code fragments

    oai_token-act-pair · gemini-2.0-flash

    colon

    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
    +:+
    -0.75
    ">—
    -0.70
     useAppContext
    -0.63
    &:
    -0.60
    :
    -0.59
    :
    
    -0.58
     ✭✭
    -0.57
    :#
    -0.57
    :&
    -0.56
     Relations
    -0.55
    POSITIVE LOGITS
    ViewChild
    0.47
    createCanvas
    0.45
     ?";
    0.44
    RectangleBorder
    0.43
    WithMany
    0.41
    ViewImports
    0.41
    acak
    0.41
     ?',
    0.41
    UnknownFieldSet
    0.41
    undefined
    0.40
    Activations Density 1.647%

    No Known Activations