© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15031
    Prev
    Next
    INDEX
    Explanations

    American Society, Academy, College

    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_13_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
     شماره
    0.59
     السؤال
    0.57
     идея
    0.56
     рр
    0.55
    ius
    0.54
     नंबर
    0.54
     нацыяна
    0.53
     رقم
    0.52
    iod
    0.52
     ܐ
    0.52
    POSITIVE LOGITS
     blacks
    0.47
     bodily
    0.45
     ordinate
    0.45
     numerosas
    0.45
    These
    0.45
     rooted
    0.44
     clicking
    0.44
     societies
    0.44
    Una
    0.44
     emitted
    0.44
    Activations Density 0.014%

    No Known Activations