© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10452
    Prev
    Next
    INDEX
    Explanations

    Ultra listings processor

    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_13_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
    er
    0.37
    t
    0.33
    ed
    0.32
    Dx
    0.31
    <
    0.30
    H
    0.29
    UD
    0.28
    Dt
    0.27
     車
    0.27
    ر
    0.27
    POSITIVE LOGITS
     Rival
    0.32
    ！)
    0.32
     competir
    0.31
    ძლი
    0.30
     Además
    0.30
     её
    0.30
     Ras
    0.30
     Bac
    0.29
     Randy
    0.29
     পড়তে
    0.29
    Activations Density 0.009%

    No Known Activations