© 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. 62587
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation and keywords

    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
    id
    0.71
    ilable
    0.59
    ikopter
    0.59
    em
    0.58
    ></
    0.58
    ang
    0.57
    os
    0.57
     grenade
    0.57
     крупней
    0.56
    appid
    0.55
    POSITIVE LOGITS
     surveillance
    0.53
    љу
    0.50
    \
    0.49
    鲷
    0.48
    裵
    0.48
     অনুসন্ধান
    0.48
    語
    0.47
     amines
    0.47
     accessoires
    0.47
     hydrolysis
    0.46
    Activations Density 0.001%

    No Known Activations