© 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. 35001
    Prev
    Next
    INDEX
    Explanations

    public services, holidays, trust, life

    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
    u
    0.67
     to
    0.62
     Astrid
    0.62
     Exploration
    0.60
    src
    0.59
     in
    0.59
     yh
    0.59
    isjon
    0.58
    z
    0.58
    zter
    0.57
    POSITIVE LOGITS
    ी
    0.66
    可
    0.55
    يته
    0.53
    филлер
    0.52
    UserModel
    0.52
    eos
    0.51
    امه
    0.50
    кает
    0.50
    茅
    0.49
    cure
    0.48
    Activations Density 0.009%

    No Known Activations