© 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. 13275
    Prev
    Next
    INDEX
    Explanations

    JavaScript function names

    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
     feces
    0.57
     நடந்தது
    0.53
     நடவடிக்கைகள்
    0.52
     攵
    0.52
     bulundu
    0.52
    ánea
    0.51
     पुरालेखित
    0.51
     on
    0.51
     రో
    0.50
     decorate
    0.50
    POSITIVE LOGITS
    that
    0.65
    This
    0.61
    Wonderful
    0.56
    That
    0.55
    S
    0.54
    this
    0.51
    spectral
    0.49
    ть
    0.48
    这个
    0.48
    Health
    0.47
    Activations Density 0.003%

    No Known Activations