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. 16288
    Prev
    Next
    INDEX
    Explanations

    adjectives preceding the word as

    oai_token-act-pair · gemini-2.0-flash

    as so

    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
    InvalidProtocol
    -0.89
    AccessorTable
    -0.85
     GenerationType
    -0.84
     propOrder
    -0.81
    MessageOf
    -0.79
     AssemblyTitle
    -0.77
     Himo
    -0.77
     wireType
    -0.77
    addContainerGap
    -0.76
     betweenstory
    -0.75
    POSITIVE LOGITS
    <bos>
    0.48
    枕
    0.42
    lay
    0.42
    läs
    0.42
    sedia
    0.41
    sieh
    0.40
    queryset
    0.40
     dây
    0.40
     it
    0.39
    '];?>
    0.38
    Activations Density 4.842%

    No Known Activations