© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193309
    Prev
    Next
    INDEX
    Explanations

    parts of a joke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     denominador
    0.46
     २०२
    0.41
    Ž
    0.40
    ciendo
    0.39
    ދ
    0.38
     collezione
    0.37
     createArticle
    0.36
     toma
    0.35
     Ston
    0.35
    ست
    0.35
    POSITIVE LOGITS
    awatts
    0.38
    William
    0.37
     outsiders
    0.35
     câu
    0.35
     jobless
    0.34
     extant
    0.33
     onwards
    0.33
    awatt
    0.33
    僱
    0.33
     seeking
    0.33
    Activations Density 0.001%

    No Known Activations