© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36959
    Prev
    Next
    INDEX
    Explanations

    */

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    íf
    0.46
    CriteriaUtils
    0.39
     Vos
    0.37
    serverResponse
    0.35
     상수
    0.35
    獼
    0.35
     рассе
    0.35
     necesitamos
    0.35
     spineItem
    0.34
     оде
    0.34
    POSITIVE LOGITS
     vars
    0.40
     laughs
    0.39
     mark
    0.39
    šnj
    0.38
    ческую
    0.38
    変
    0.38
    ulsions
    0.38
    뜹
    0.37
    emarks
    0.37
    chunks
    0.37
    Activations Density 0.001%

    No Known Activations