© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 36115
    Prev
    Next
    INDEX
    Explanations

    academic or work tasks

    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_7_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
    us
    0.71
    ρα
    0.55
    ០
    0.52
    in
    0.52
    ٤
    0.51
    т
    0.51
    de
    0.50
    elle
    0.49
    ad
    0.48
     доставка
    0.48
    POSITIVE LOGITS
    ?
    0.58
    い
    0.57
    HY
    0.55
    מי
    0.55
    Hope
    0.54
    speople
    0.53
     יותר
    0.53
    מה
    0.52
    Bare
    0.52
    "
    0.52
    Activations Density 0.025%

    No Known Activations