© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217502
    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_50_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
    CIS
    0.41
     CIS
    0.41
    cis
    0.41
    amir
    0.38
     किश
    0.37
    john
    0.37
    옥
    0.36
    fetch
    0.36
    Cham
    0.36
    જ
    0.35
    POSITIVE LOGITS
     As
    0.44
    As
    0.40
    ystyrene
    0.40
     kèo
    0.39
     ܐ
    0.39
    රක
    0.38
    にかく
    0.38
    ᱝ
    0.38
     espada
    0.36
    QUARE
    0.36
    Activations Density 0.000%

    No Known Activations