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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14132
    Prev
    Next
    INDEX
    Explanations

    lines of asterisks in code

    oai_token-act-pair · gemini-2.0-flash

    Asterisks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    ****************
    -0.76
     Theſe
    -0.65
    rophes
    -0.65
     Beſ
    -0.65
    Тогда
    -0.64
    doria
    -0.64
    EClass
    -0.63
    ISupport
    -0.63
    ***********
    -0.62
    XtraEditors
    -0.62
    POSITIVE LOGITS
    <bos>
    0.71
    ↵
    0.68
    ’
    0.57
    ”
    0.54
    '
    0.53
    <code>
    0.50
    <em>
    0.50
    "
    0.48
    “
    0.47
    #
    0.46
    Activations Density 0.721%

    No Known Activations