© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215044
    Prev
    Next
    INDEX
    Explanations

    `)) {

    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_31_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
    ++){
    0.38
    rono
    0.38
     situate
    0.38
     prét
    0.37
     внимание
    0.36
    扱い
    0.36
    -+
    0.36
    $...
    0.35
     drawn
    0.35
    VERTISING
    0.35
    POSITIVE LOGITS
     Barnard
    0.40
     masker
    0.38
     RES
    0.38
     granular
    0.38
    indexer
    0.38
     Oskar
    0.38
     sol
    0.37
     много
    0.37
     Bant
    0.37
     diagnosis
    0.37
    Activations Density 0.000%

    No Known Activations