© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 168087
    Prev
    Next
    INDEX
    Explanations

    Legends

    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_31_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
    ALI
    0.28
    Arrange
    0.27
    Bins
    0.26
    Machines
    0.26
    大法
    0.26
    ম্‌
    0.26
    Transfer
    0.25
    Lam
    0.25
    Caching
    0.25
     -----
    0.25
    POSITIVE LOGITS
    하거나
    0.30
    욬
    0.29
    するなど
    0.28
     অথবা
    0.28
    거나
    0.28
     लिहा
    0.27
     RFC
    0.27
    hit
    0.27
     imm
    0.26
     imaginable
    0.26
    Activations Density 0.006%

    No Known Activations