© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211871
    Prev
    Next
    INDEX
    Explanations

    discretizing data into bins

    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_20_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
     barely
    0.38
    More
    0.37
    बे
    0.36
    AI
    0.35
    炤
    0.34
    Trails
    0.33
    III
    0.32
    three
    0.32
     More
    0.32
    Einstein
    0.32
    POSITIVE LOGITS
    ousedown
    0.31
     abdominal
    0.31
     Md
    0.31
     сторону
    0.29
    ">%
    0.29
    ായിക
    0.29
    อน
    0.29
    TabText
    0.29
    illust
    0.28
    ském
    0.28
    Activations Density 0.004%

    No Known Activations