© 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. 148500
    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
     вы
    0.49
    нной
    0.48
     поради
    0.47
     хотят
    0.46
     ר
    0.46
     corruption
    0.44
     поэ
    0.44
     pu
    0.43
     وط
    0.43
     מו
    0.43
    POSITIVE LOGITS
     Tint
    0.49
     Adhesive
    0.44
    ↵
    0.43
    steins
    0.42
    规
    0.41
     Helper
    0.41
    helper
    0.41
    marking
    0.39
    tint
    0.39
    芒果
    0.39
    Activations Density 0.000%

    No Known Activations