© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41330
    Prev
    Next
    INDEX
    Explanations

    video, Ubuntu, gay, dioxide

    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_22_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
    溆
    0.33
     αλλά
    0.32
    rugada
    0.31
    平时
    0.28
     கணி
    0.28
    ศิลป
    0.28
    ícul
    0.27
     erfol
    0.27
    '");
    0.27
     :{
    0.27
    POSITIVE LOGITS
     Powered
    0.33
     Joe
    0.32
     distract
    0.31
     distracted
    0.29
     followed
    0.29
    Maximum
    0.29
     DLC
    0.29
     maximum
    0.28
     Maximum
    0.28
     Video
    0.27
    Activations Density 0.037%

    No Known Activations