© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67490
    Prev
    Next
    INDEX
    Explanations

    bulls

    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_41_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
     निकालते
    0.43
     }]);
    0.39
     კომ
    0.37
     निकालेंगे
    0.36
    RAJ
    0.36
     הסי
    0.36
     निकालने
    0.36
     δρα
    0.35
     大
    0.35
    以
    0.35
    POSITIVE LOGITS
     dispersal
    0.42
     dispersions
    0.39
     попа
    0.38
     Dais
    0.38
    iyaç
    0.38
    Caught
    0.37
    qp
    0.36
     создан
    0.36
    Epid
    0.36
    딧
    0.36
    Activations Density 0.001%

    No Known Activations