© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33550
    Prev
    Next
    INDEX
    Explanations

    4xx or 5xx error codes

    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_40_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
    setMessage
    0.45
     set
    0.37
     aq
    0.37
     변
    0.36
    SET
    0.35
     SET
    0.35
    preg
    0.35
     positive
    0.35
     variable
    0.35
     mù
    0.35
    POSITIVE LOGITS
    alan
    0.38
    访问
    0.36
    践
    0.36
    SleepHours
    0.36
    Cline
    0.36
    URNS
    0.35
    Drinking
    0.35
     তাজ
    0.35
    Penumpang
    0.34
     Hesse
    0.34
    Activations Density 0.004%

    No Known Activations