© 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. 51678
    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
    0.70
    1
    0.55
    8
    0.51
     Finger
    0.46
     duplicate
    0.46
    7
    0.44
     dual
    0.43
     Reverse
    0.43
     Dual
    0.42
     Jacobs
    0.42
    POSITIVE LOGITS
    اين
    0.51
    getPlayer
    0.50
    وك
    0.49
     Educação
    0.49
    restaurant
    0.49
    在
    0.48
     voyez
    0.47
    μον
    0.47
    رس
    0.47
    मताओं
    0.46
    Activations Density 0.000%

    No Known Activations