© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35058
    Prev
    Next
    INDEX
    Explanations

    throat, larynx, swallowing

    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
    Negative Logits
    ΑΣ
    0.61
    НЫ
    0.60
    <0x8C>
    0.60
    heureusement
    0.60
    ईआरटी
    0.59
     습
    0.58
     ያስ
    0.57
    ERTY
    0.56
     одну
    0.56
    TRIGGER
    0.56
    POSITIVE LOGITS
    de
    0.62
     de
    0.59
     ταιν
    0.57
    Movie
    0.55
     într
    0.55
    o
    0.54
    iled
    0.54
     împ
    0.54
     canoe
    0.53
     hasta
    0.53
    Activations Density 0.033%

    No Known Activations