© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67702
    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_41_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
    otene
    0.42
    Feign
    0.39
     hypoc
    0.38
     фе
    0.38
    Fel
    0.37
    텍
    0.37
     Fel
    0.36
     fel
    0.36
     Prot
    0.36
    ફે
    0.36
    POSITIVE LOGITS
     PC
    0.40
     अबू
    0.39
     mittels
    0.39
    ImageBox
    0.39
    superblock
    0.38
     görünt
    0.37
     couvre
    0.37
     Suprema
    0.37
     distant
    0.36
    㧡
    0.36
    Activations Density 0.003%

    No Known Activations