© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247998
    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_56_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
     ακό
    0.51
     US
    0.47
     фі
    0.45
     FOLLOWING
    0.45
     vudd
    0.43
     seguintes
    0.43
     следующих
    0.42
    விர
    0.41
     seguente
    0.40
     (*)
    0.40
    POSITIVE LOGITS
    ～
    0.42
     pricey
    0.38
    Susan
    0.38
    ?—
    0.38
    〜
    0.37
    expensive
    0.37
    Rachel
    0.37
    "—
    0.37
    ～。
    0.37
    鈥
    0.36
    Activations Density 0.000%

    No Known Activations