© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174713
    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_24_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
    Finland
    0.53
    ė
    0.51
    nici
    0.49
    куляр
    0.49
     സംഭവ
    0.49
    ethylamine
    0.48
    nosť
    0.46
    Discard
    0.45
     चलना
    0.45
    Cyan
    0.44
    POSITIVE LOGITS
    瓮
    0.46
     stranger
    0.46
    geti
    0.45
     paperwork
    0.44
     Saks
    0.44
     creeps
    0.44
     ie
    0.44
     любы
    0.44
     competes
    0.43
     деп
    0.43
    Activations Density 0.000%

    No Known Activations