© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142426
    Prev
    Next
    INDEX
    Explanations

    lighting fixtures

    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_12_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
    スト
    0.60
    ﻡ
    0.55
     کردم
    0.54
    peliculas
    0.54
    த்துடன்
    0.52
    ເພ
    0.51
    স্প
    0.50
    家乐
    0.50
    стам
    0.50
     стрельца
    0.50
    POSITIVE LOGITS
     (
    0.70
     [
    0.64
     shoe
    0.59
    ff
    0.51
     -(
    0.51
     fob
    0.50
     linker
    0.49
    h
    0.49
     잡
    0.48
     interpolate
    0.48
    Activations Density 0.000%

    No Known Activations