© 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. 217741
    Prev
    Next
    INDEX
    Explanations

    Hyphens

    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
     punk
    0.41
     Punk
    0.40
    мы
    0.40
    미
    0.40
     pubis
    0.39
    openia
    0.39
    llium
    0.38
    mi
    0.38
    प्रधान
    0.38
    myLabels
    0.38
    POSITIVE LOGITS
    نتی
    0.40
     Corso
    0.38
     Wordsworth
    0.38
     corr
    0.37
    спек
    0.37
     स्नातक
    0.37
     J
    0.36
     よ
    0.36
     Spears
    0.36
     caged
    0.36
    Activations Density 0.000%

    No Known Activations