© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 128882
    Prev
    Next
    INDEX
    Explanations

    ab + non-ab character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ↵↵
    1.23
    ก
    1.10
     commande
    1.09
     može
    1.06
     faisait
    1.04
     comprende
    1.04
    zelfde
    0.99
     pokazuje
    0.99
     oferece
    0.98
     pouvait
    0.96
    POSITIVE LOGITS
    0
    1.27
    5
    1.04
    را
    1.03
    in
    0.94
    mpg
    0.93
    ;
    0.92
    .
    0.90
    .",
    0.89
    7
    0.86
    riers
    0.85
    Activations Density 0.000%

    No Known Activations