© 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. 36974
    Prev
    Next
    INDEX
    Explanations

    F1 racing news and lists

    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
    ள்ளி
    0.39
    मूर्ति
    0.35
     پوچھ
    0.34
    iban
    0.33
     llen
    0.32
     ")";
    0.32
    athin
    0.32
    adeon
    0.32
    Stefan
    0.31
     ")");
    0.31
    POSITIVE LOGITS
     Jazz
    0.38
    ဒ
    0.36
    Jazz
    0.35
     jazz
    0.34
    jazz
    0.33
    犠
    0.33
    window
    0.31
    jac
    0.31
     rigs
    0.31
    季節
    0.31
    Activations Density 0.007%

    No Known Activations