© 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. 148614
    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
    Not in Any Lists

    No Comments

    Negative Logits
    滘
    0.38
    жко
    0.38
     pemrograman
    0.37
     роль
    0.36
     بگ
    0.35
     смогут
    0.35
     কর্তৃপক্ষ
    0.34
     stellte
    0.34
    မြ
    0.33
     можуть
    0.33
    POSITIVE LOGITS
     trees
    0.43
    ">(
    0.43
    ビン
    0.41
     foliage
    0.40
     defense
    0.39
    eu
    0.39
     tree
    0.39
     part
    0.39
     fractional
    0.39
     pairs
    0.39
    Activations Density 0.000%

    No Known Activations