© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8698
    Prev
    Next
    INDEX
    Explanations

    luxury option or std generic

    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_13_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
     tương
    0.33
     weiter
    0.31
    ці
    0.29
     etwa
    0.29
    IF
    0.28
     trại
    0.28
    ería
    0.28
    haft
    0.27
     व
    0.27
    ро
    0.27
    POSITIVE LOGITS
     Перед
    0.33
     Registration
    0.31
     Результа
    0.31
     \
    0.30
     Username
    0.30
     Complete
    0.29
     "&#
    0.29
    Перед
    0.29
     کوشش
    0.29
     Formulation
    0.29
    Activations Density 0.010%

    No Known Activations