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. 16366
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and variables

    oai_token-act-pair · gemini-2.0-flash

    $

    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
     Wikimédia
    -0.63
    既
    -0.55
    ๋
    -0.45
     which
    -0.45
     sportivo
    -0.44
    flink
    -0.41
     duquel
    -0.41
     auszu
    -0.41
    ligare
    -0.41
    まで
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.88
     متعلقه
    0.81
     صوتيه
    0.78
    حوالہ
    0.69
    loroethene
    0.68
     contextLoads
    0.66
    Enllaces
    0.65
     للمعارف
    0.65
    "}";
    0.62
    ())));
    0.62
    Activations Density 3.437%

    No Known Activations