© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247972
    Prev
    Next
    INDEX
    Explanations

    Video

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     동
    1.07
     ví
    1.00
     ві
    0.86
    동
    0.84
    ví
    0.81
    Ví
    0.75
     Ví
    0.70
     ヴィ
    0.68
    维
    0.67
     ვი
    0.65
    POSITIVE LOGITS
     Video
    1.65
     video
    1.57
    Video
    1.56
    video
    1.53
     Vide
    1.38
     видео
    1.34
    Vide
    1.31
    视频
    1.30
     वीडियो
    1.29
     VIDEO
    1.29
    Activations Density 0.011%

    No Known Activations