© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6214
    Prev
    Next
    INDEX
    Explanations

    в + word

    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_40_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
    through
    0.52
     through
    0.49
    Through
    0.44
     THROUGH
    0.41
     Through
    0.41
    を通して
    0.39
    通过
    0.38
    deal
    0.38
    尒
    0.37
     moose
    0.36
    POSITIVE LOGITS
    弄
    0.37
     الدع
    0.37
     aon
    0.36
     масштаб
    0.36
    떄
    0.36
    逢
    0.36
    حث
    0.35
     Zn
    0.34
     Dun
    0.34
    ,''
    0.34
    Activations Density 0.011%

    No Known Activations