© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41274
    Prev
    Next
    INDEX
    Explanations

    wash, put, throw, give

    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_11_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
    0.55
     குழ
    0.45
     عندي
    0.44
     dxc
    0.44
    ذلك
    0.43
    зия
    0.42
     tı
    0.42
     другое
    0.42
    ımı
    0.42
    ęcie
    0.42
    POSITIVE LOGITS
     P
    0.48
     Animator
    0.44
     L
    0.44
     Throwable
    0.43
    RA
    0.42
     Jul
    0.42
     Foods
    0.41
     Recipe
    0.41
       
    0.41
     Motorsports
    0.40
    Activations Density 0.029%

    No Known Activations