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. 16255
    Prev
    Next
    INDEX
    Explanations

    code snippets with fields and properties, especially ones involving UInt, Int, Fixed, and Sfixed.

    oai_token-act-pair · gemini-2.0-flash

    punctuation/syntax

    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
     pinulongan
    -0.78
     ExecuteAsync
    -0.77
     useAppContext
    -0.76
     myſelf
    -0.75
     fubject
    -0.73
     Shakspeare
    -0.71
    WriteTagHelper
    -0.70
     Cæsar
    -0.70
     pleaſure
    -0.70
    awtextra
    -0.69
    POSITIVE LOGITS
     هيا
    0.50
     ран
    0.47
    Portale
    0.47
    argli
    0.46
     distanciation
    0.45
     larga
    0.43
    кта
    0.43
    :✨
    0.43
     Gar
    0.43
    рай
    0.41
    Activations Density 15.224%

    No Known Activations