© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154663
    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_23_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
    I
    0.49
    ﹟
    0.46
     называется
    0.45
    наче
    0.45
    лго
    0.45
    O
    0.45
    По
    0.44
     consumable
    0.44
    ो
    0.43
    เปลี่ยน
    0.42
    POSITIVE LOGITS
     Museums
    0.54
     Box
    0.53
     Araújo
    0.51
     Mobile
    0.49
     Mad
    0.49
     Tri
    0.47
     খুঁজ
    0.47
     Kiến
    0.46
     Fever
    0.46
     Super
    0.44
    Activations Density 0.000%

    No Known Activations