© 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. 210328
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ្នក
    0.51
     protégé
    0.51
    ptitle
    0.50
     फस
    0.49
    ᅴ
    0.49
     πάν
    0.49
     मध्य
    0.48
    ský
    0.47
     മുന്ന
    0.47
    ských
    0.47
    POSITIVE LOGITS
    h
    0.49
     EVER
    0.42
    ONE
    0.42
     ANOTHER
    0.42
     iza
    0.40
     cela
    0.40
     Cela
    0.40
     tabella
    0.39
     அவரை
    0.39
    imed
    0.39
    Activations Density 0.000%

    No Known Activations