© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193671
    Prev
    Next
    INDEX
    Explanations

    goat, livestock, and animals

    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_15_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
    is
    0.61
    cta
    0.59
     scena
    0.55
    mood
    0.52
     have
    0.51
    have
    0.51
     evoke
    0.50
     reject
    0.49
    ity
    0.49
    ️
    0.48
    POSITIVE LOGITS
     increments
    0.54
     necessário
    0.50
     helplessly
    0.50
     আপনি
    0.50
     해외
    0.50
     Việc
    0.50
     नए
    0.48
    rivastava
    0.48
     Chowdhury
    0.48
    新しい
    0.48
    Activations Density 0.000%

    No Known Activations