© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121620
    Prev
    Next
    INDEX
    Explanations

    Crab Rangoon / Crab cakes

    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_3_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
    ى
    0.67
     самого
    0.60
    м
    0.57
    ம்
    0.55
    ويه
    0.55
     revolved
    0.54
    пе
    0.53
    υ
    0.53
    ன்
    0.52
    يو
    0.52
    POSITIVE LOGITS
     are
    0.82
    া
    0.81
    at
    0.73
     Kabir
    0.71
    in
    0.70
    Athens
    0.70
    _
    0.67
    ty
    0.66
    ow
    0.64
     out
    0.64
    Activations Density 0.000%

    No Known Activations