© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40557
    Prev
    Next
    INDEX
    Explanations

    audiobooks and books

    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_3_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
     be
    0.87
    ↵
    0.80
     (
    0.73
    ký
    0.68
    ك
    0.66
    og
    0.65
    у
    0.65
    ون
    0.64
    Grocery
    0.63
    ا
    0.61
    POSITIVE LOGITS
     slalom
    0.66
    الہ
    0.66
     incidental
    0.64
     حرکت
    0.60
     intrauterine
    0.60
    必要な
    0.59
    i
    0.57
    autiful
    0.57
    ꘏
    0.57
     neutrino
    0.56
    Activations Density 0.004%

    No Known Activations