© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84050
    Prev
    Next
    INDEX
    Explanations

    sales, people, and efforts

    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_23_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
     Smart
    0.36
     obnoxious
    0.35
    悅
    0.34
     Thacker
    0.33
     Microsoft
    0.32
     ቤ
    0.32
    Rez
    0.32
     scar
    0.31
     राजप
    0.31
     personal
    0.31
    POSITIVE LOGITS
    자에
    0.36
    ành
    0.35
    jml
    0.34
     OBJECTTYPE
    0.34
    beer
    0.33
    %@",
    0.33
    WARF
    0.33
    Plas
    0.33
    Beer
    0.33
     వరకు
    0.33
    Activations Density 0.005%

    No Known Activations