© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40683
    Prev
    Next
    INDEX
    Explanations

    descriptions and details

    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_57_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
     συμβ
    0.43
     еди
    0.38
    ván
    0.38
    σιά
    0.38
    চা
    0.38
    oving
    0.37
     Crops
    0.37
    뵌
    0.37
    rma
    0.37
     Grat
    0.36
    POSITIVE LOGITS
    Daemon
    0.40
    Hat
    0.39
     внимания
    0.38
    <unused67>
    0.38
    Blade
    0.38
    ни
    0.37
    ني
    0.37
     nihil
    0.36
    sans
    0.36
    ниями
    0.35
    Activations Density 0.001%

    No Known Activations