© 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. 257323
    Prev
    Next
    INDEX
    Explanations

    given or provided materials/tasks

    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
    Negative Logits
    رف
    0.25
    買
    0.23
    买
    0.22
    గు
    0.22
    น
    0.22
     заку
    0.22
     Cult
    0.21
    鑑定
    0.21
    生命
    0.21
     Fred
    0.21
    POSITIVE LOGITS
     hydraz
    0.26
    stackpath
    0.26
    chnen
    0.25
    Polygon
    0.24
    NaBH
    0.24
    𝙤
    0.24
    ὴν
    0.24
     dichas
    0.24
     calificaciones
    0.23
    ябрь
    0.23
    Activations Density 0.003%

    No Known Activations