© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63012
    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_46_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
     def
    0.55
     offered
    0.43
     Folk
    0.40
     naturally
    0.39
     cubs
    0.39
     Fox
    0.39
     DEF
    0.39
    篭
    0.38
     Linn
    0.38
     Lore
    0.38
    POSITIVE LOGITS
    ursed
    0.39
    物理
    0.38
     динами
    0.38
    zęd
    0.38
    शक
    0.38
    Dyn
    0.38
    Yun
    0.37
    phan
    0.37
    ceğim
    0.37
     गतिशील
    0.36
    Activations Density 0.000%

    No Known Activations