© 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. 203955
    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
    Not in Any Lists

    No Comments

    Negative Logits
    Michigan
    0.35
    眼里
    0.35
     Laver
    0.34
     h
    0.33
     VX
    0.33
     Karel
    0.33
     fees
    0.32
    Nev
    0.32
     عائد
    0.32
    ე
    0.32
    POSITIVE LOGITS
    索
    1.14
    ソ
    1.13
     Со
    1.11
    โซ
    1.09
     सो
    1.02
     Sow
    0.97
     সো
    0.97
     ソ
    0.97
    소
    0.97
    Со
    0.96
    Activations Density 0.000%

    No Known Activations