© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 44996
    Prev
    Next
    INDEX
    Explanations

    Honda car models

    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_10_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
     I
    1.00
     Turkish
    0.99
     Türkei
    0.95
     Ottoman
    0.90
    Turkish
    0.87
     Ankara
    0.85
     Istanbul
    0.84
     Fenerbah
    0.84
     (
    0.82
     EN
    0.80
    POSITIVE LOGITS
    н
    0.99
    n
    0.94
    ";
    0.86
    er
    0.82
    );
    0.81
    0
    0.77
    )
    0.73
    are
    0.72
    )。
    0.72
    анд
    0.71
    Activations Density 0.002%

    No Known Activations