© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92507
    Prev
    Next
    INDEX
    Explanations

    for (int i

    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_11_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
    )‏
    0.59
     котором
    0.57
    霭
    0.57
    etli
    0.57
    šti
    0.57
    人不
    0.56
     which
    0.55
     яких
    0.55
     שמ
    0.53
    odynam
    0.53
    POSITIVE LOGITS
     [
    0.60
    其他
    0.60
    in
    0.60
    letzt
    0.57
     .
    0.54
     litros
    0.53
    讫
    0.52
    ुद्ध
    0.52
    ла
    0.51
    ម្លៃ
    0.51
    Activations Density 0.001%

    No Known Activations