© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46258
    Prev
    Next
    INDEX
    Explanations

    reading, teaching, building, filling

    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_22_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
    ட்சத்திர
    0.40
    就在
    0.40
     নাহি
    0.40
     artery
    0.39
    etheless
    0.39
    conder
    0.38
    ゙
    0.38
    োন
    0.38
     decreasing
    0.38
     vein
    0.38
    POSITIVE LOGITS
    Wel
    0.40
    했고
    0.39
    🇲
    0.39
     हॉस्पिटल
    0.38
    Colombia
    0.38
     فری
    0.37
     homeschooling
    0.37
    멕
    0.37
     résult
    0.37
    Bitcoin
    0.37
    Activations Density 0.017%

    No Known Activations