© 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. 48192
    Prev
    Next
    INDEX
    Explanations

    lines ending in colon or period

    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
    िलेश
    0.31
     Pb
    0.30
     Computation
    0.29
    hnung
    0.29
    pann
    0.29
    omás
    0.29
     sor
    0.28
    azy
    0.28
    绷
    0.28
     grunt
    0.28
    POSITIVE LOGITS
    ##
    0.34
    Developed
    0.32
    alassemia
    0.31
    $=\
    0.30
    $\
    0.30
    ൩
    0.30
    osperm
    0.30
    ごとに
    0.29
     спря
    0.29
    ześnie
    0.29
    Activations Density 0.000%

    No Known Activations