© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238608
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_32_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
     मानी
    0.28
    ============
    0.27
     تحصیل
    0.27
     predmet
    0.27
    cycl
    0.26
    ober
    0.25
    backing
    0.25
    ===
    0.25
    fly
    0.25
    diaz
    0.25
    POSITIVE LOGITS
    Ể
    0.28
     найкра
    0.27
     Candles
    0.27
    Й
    0.26
     intersections
    0.26
    ້
    0.26
    έν
    0.26
     INTERACTIONS
    0.25
    犒
    0.25
    Cand
    0.25
    Activations Density 0.000%

    No Known Activations