© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238335
    Prev
    Next
    INDEX
    Explanations

    input prompts ending in parenthesis

    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_32_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
    (`#
    0.42
     अंडरस्टैंड
    0.41
    лую
    0.40
    Generated
    0.39
     moder
    0.38
     Wants
    0.38
    Selecting
    0.38
     kusal
    0.38
     estuvieron
    0.37
     #(
    0.36
    POSITIVE LOGITS
    opter
    0.37
     manches
    0.36
     McM
    0.35
    ningar
    0.35
     bubbles
    0.35
     sideWeight
    0.35
    pson
    0.35
    presentation
    0.34
    orro
    0.34
    hov
    0.34
    Activations Density 0.005%

    No Known Activations