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. 16312
    Prev
    Next
    INDEX
    Explanations

    elements of a recipe or instructions

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
     pleaſure
    -0.99
     AssemblyCulture
    -0.91
     Theſe
    -0.90
     itſelf
    -0.86
     themſelves
    -0.86
     myſelf
    -0.85
    HasForeignKey
    -0.85
    ngdoc
    -0.85
    ſelves
    -0.84
     greateſt
    -0.81
    POSITIVE LOGITS
    <eos>
    0.71
    ,
    0.47
     -
    0.45
    め
    0.45
    row
    0.43
     […]
    0.41
    *
    0.41
    iel
    0.40
    (
    0.38
    C
    0.38
    Activations Density 7.726%

    No Known Activations