Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16242
    Prev
    Next
    INDEX
    Explanations

    parenthesized numbers and citation information

    oai_token-act-pair · gemini-2.0-flash

    parenthesized numbers

    np_token-act-pair-logits · gemini-2.0-flash

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    AndEndTag
    -0.80
     دیکھیے
    -0.76
    fjspx
    -0.66
     Exactos
    -0.63
     ویکی‌پدی
    -0.61
     kaarangay
    -0.60
    ыгана
    -0.60
    InputBorder
    -0.59
    SourceChecksum
    -0.59
    ंदीखरीदारी
    -0.56
    POSITIVE LOGITS
     sessionFactory
    0.54
    JoinColumn
    0.50
     Wachs
    0.49
    pruch
    0.48
    (@
    0.47
    écnicas
    0.47
    labelledby
    0.46
    LError
    0.45
     tận
    0.45
    Relacion
    0.45
    Activations Density 0.567%

    No Known Activations