© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217680
    Prev
    Next
    INDEX
    Explanations

    power grids

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    នៃការ
    0.41
     Jol
    0.41
     Drone
    0.40
     Force
    0.40
     Malone
    0.39
     Chong
    0.38
     ဗ
    0.38
     Drav
    0.38
    Drone
    0.37
     Virginia
    0.36
    POSITIVE LOGITS
    出
    0.42
    *}
    0.41
    OGA
    0.41
    Out
    0.40
     fflush
    0.40
     )}$
    0.39
    InOut
    0.39
     out
    0.38
     буква
    0.38
    Prep
    0.38
    Activations Density 0.002%

    No Known Activations