© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170216
    Prev
    Next
    INDEX
    Explanations

    entry point

    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_20_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
     extremes
    0.50
     محض
    0.43
    ޅ
    0.43
    ું
    0.42
     nibh
    0.42
    퉁
    0.42
     була
    0.42
    ทรวง
    0.42
    ць
    0.41
     pública
    0.41
    POSITIVE LOGITS
     assure
    0.48
     +\
    0.44
    ala
    0.44
     Locations
    0.43
     Lo
    0.43
    ech
    0.42
     Artes
    0.42
     assuring
    0.42
     Lauren
    0.41
     разли
    0.41
    Activations Density 0.000%

    No Known Activations