© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142308
    Prev
    Next
    INDEX
    Explanations

    panoramic views

    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_12_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
    about
    0.53
     bý
    0.52
    Gum
    0.52
     humbled
    0.50
    zeum
    0.50
     бизнеса
    0.50
     ህ
    0.50
    About
    0.49
     次
    0.49
    Hung
    0.48
    POSITIVE LOGITS
    attering
    0.57
    anilide
    0.57
    ленная
    0.55
    astic
    0.55
    İ
    0.54
    ului
    0.54
     واکنش
    0.54
    ST
    0.54
     Macedonian
    0.53
     İstanbul
    0.53
    Activations Density 0.000%

    No Known Activations