© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254106
    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_56_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
     H
    0.41
     اله
    0.39
    意
    0.38
     hàng
    0.37
    H
    0.37
     হ
    0.34
    iod
    0.34
     ह
    0.34
     ห
    0.34
    வில
    0.33
    POSITIVE LOGITS
    主
    1.45
    主的
    1.05
    的主
    1.03
     chủ
    1.02
     主
    0.96
     Chủ
    0.89
     Main
    0.71
     главный
    0.70
     주
    0.66
    Main
    0.66
    Activations Density 0.000%

    No Known Activations