© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103246
    Prev
    Next
    INDEX
    Explanations

    resolution, encoding, rewrite

    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_16_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
    字幕
    0.42
    KeyDown
    0.42
    坂
    0.41
    starts
    0.41
    harap
    0.40
    的一些
    0.40
    Amazon
    0.39
    ström
    0.38
    semantics
    0.38
    schemas
    0.38
    POSITIVE LOGITS
     ou
    0.62
     Ou
    0.58
    ý
    0.57
     été
    0.56
    ou
    0.55
    iy
    0.55
     desenvolvido
    0.54
    ها
    0.52
     dziecko
    0.50
    পৃথিব
    0.49
    Activations Density 0.000%

    No Known Activations