© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51785
    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_10_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
    (
    0.49
     antennis
    0.47
     می‌ده
    0.46
    Downloading
    0.46
    觀眾
    0.46
     vann
    0.46
     suara
    0.45
    /~
    0.45
     ভিক্ষ
    0.45
    ῃ
    0.45
    POSITIVE LOGITS
     Acme
    0.44
     very
    0.44
     Region
    0.44
    া
    0.43
    dus
    0.42
     Reg
    0.42
    源
    0.42
     ridicule
    0.42
     மிகு
    0.41
    regate
    0.41
    Activations Density 0.000%

    No Known Activations