© 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. 205464
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    比特币
    0.49
    Carbon
    0.49
    自主
    0.49
    рино
    0.49
    اقة
    0.46
    稣
    0.46
    涵盖
    0.45
    ిన
    0.44
    准备
    0.44
    Disk
    0.43
    POSITIVE LOGITS
     y
    0.53
     e
    0.49
     archaeologist
    0.47
     underdeveloped
    0.46
     desa
    0.46
     cl
    0.45
     los
    0.45
     coarse
    0.45
     peter
    0.45
    %,
    0.44
    Activations Density 0.000%

    No Known Activations