© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83624
    Prev
    Next
    INDEX
    Explanations

    formula

    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_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    와의
    1.29
    ுடன்
    1.20
    я
    1.15
    ু
    1.13
     О
    1.11
    ップ
    1.10
    acchati
    1.10
    èbres
    1.09
     Yatha
    1.09
     Союза
    1.09
    POSITIVE LOGITS
     is
    2.53
     of
    1.65
     in
    1.56
    ↵↵
    1.53
    ,
    1.45
    .
    1.44
    ↵
    1.34
     (
    1.31
     $
    1.29
    在
    1.28
    Activations Density 0.001%

    No Known Activations