© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136287
    Prev
    Next
    INDEX
    Explanations

    time horizon

    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_12_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
    '
    0.50
     action
    0.46
    ٥
    0.44
     héro
    0.44
    ’
    0.43
    </td>
    0.42
    బడు
    0.42
     probative
    0.41
    제의
    0.41
     “[
    0.41
    POSITIVE LOGITS
     প্যাকে
    0.53
     вашей
    0.49
    wią
    0.48
     आपकी
    0.48
     samano
    0.47
     Thessaloniki
    0.47
     iyong
    0.47
     Saxony
    0.47
     ваша
    0.46
     profissionais
    0.46
    Activations Density 0.000%

    No Known Activations