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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1572
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols in the context of physics

    oai_token-act-pair · gemini-2.0-flash

    scientific/math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     виправивши
    -1.03
     betweenstory
    -0.96
    CloseOperation
    -0.85
     utafitiHapana
    -0.82
    :✨
    -0.81
    évaluateur
    -0.80
     initComponents
    -0.79
     Paglinawan
    -0.77
    SourceChecksum
    -0.74
    Παραπομπές
    -0.73
    POSITIVE LOGITS
    }}_
    0.63
    _\
    0.63
    $\
    0.63
    ^(
    0.63
    (\
    0.62
    ^\
    0.58
    _{{\
    0.57
    ^{
    0.56
    (${
    0.56
    {\
    0.56
    Activations Density 11.457%

    No Known Activations