© 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. 41188
    Prev
    Next
    INDEX
    Explanations

    API endpoints: items, users, todos

    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
    Negative Logits
     egregious
    0.42
    erun
    0.41
     Richard
    0.41
     Iwas
    0.38
    神
    0.38
     చేశారు
    0.38
    প্রতি
    0.37
     Alhamdulillah
    0.37
    viene
    0.37
     செய்தனர்
    0.37
    POSITIVE LOGITS
    телю
    0.42
    诅
    0.41
    ский
    0.38
    ouring
    0.38
    HYDRO
    0.37
     json
    0.36
    ："
    0.36
    INDEX
    0.36
    终止
    0.36
    scription
    0.36
    Activations Density 0.001%

    No Known Activations