© 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. 194878
    Prev
    Next
    INDEX
    Explanations

    at

    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
    emplace
    0.37
     BO
    0.37
    天下
    0.36
     парла
    0.36
     REI
    0.35
    erva
    0.35
    ująca
    0.34
    慮
    0.34
    AS
    0.34
     Transl
    0.33
    POSITIVE LOGITS
     met
    0.47
    adors
    0.41
     মিটার
    0.41
    chid
    0.40
    mimeTypes
    0.38
    एक
    0.38
     apod
    0.38
    ሽን
    0.37
    Tensor
    0.37
     チェ
    0.36
    Activations Density 0.003%

    No Known Activations