© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83892
    Prev
    Next
    INDEX
    Explanations

    dialogue quoted after "he said" or "she said"

    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_29_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
     mètres
    0.41
     व्याकरण
    0.38
    ogiri
    0.38
     رہنے
    0.38
    ಗೊಳ್ಳ
    0.37
     Datensch
    0.36
     एकड़
    0.35
     ***!
    0.35
     बेहत
    0.34
     ஏக்க
    0.34
    POSITIVE LOGITS
    ｢
    0.36
     "
    0.35
     “(
    0.35
     (
    0.35
     Ос
    0.34
     Ties
    0.34
     "(
    0.33
     utilizes
    0.33
    '(
    0.33
     snapped
    0.33
    Activations Density 0.008%

    No Known Activations