© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193245
    Prev
    Next
    INDEX
    Explanations

    data processing: normalization, assembly, buffering

    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_27_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
     Academy
    0.37
     পল
    0.37
     Dunlop
    0.37
     초기
    0.35
    ovsky
    0.34
    又
    0.34
     abortion
    0.33
     পা
    0.33
     utilisé
    0.33
    我们在
    0.33
    POSITIVE LOGITS
    doFilter
    0.42
    SimpleDateFormat
    0.42
     crevices
    0.41
    ಡಿದ
    0.38
     unification
    0.38
     filtros
    0.37
    MATCH
    0.37
     OUTPUT
    0.36
    緣
    0.36
     گرفته
    0.36
    Activations Density 0.019%

    No Known Activations