© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103103
    Prev
    Next
    INDEX
    Explanations

    surgery descriptions

    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_16_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     případ
    0.55
    vendo
    0.54
    ਿਲ
    0.53
    Task
    0.52
    بعد
    0.51
    ږد
    0.51
    ειας
    0.49
    톄
    0.49
    ဇ
    0.49
     تقدر
    0.48
    POSITIVE LOGITS
     fraudulent
    0.52
     clenched
    0.52
    ali
    0.51
    ™
    0.48
     tarp
    0.48
    alee
    0.48
     материалы
    0.47
     it
    0.47
     leash
    0.47
    ?
    0.47
    Activations Density 0.000%

    No Known Activations