© 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. 171017
    Prev
    Next
    INDEX
    Explanations

    wheel

    np_max-act-logits · gemini-2.5-flash-lite
    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
     கண்டி
    0.38
    lty
    0.33
    ндо
    0.33
     explotación
    0.32
     comprends
    0.32
    IMG
    0.32
    ariate
    0.31
    ங
    0.31
    ጫ
    0.31
    ूँ
    0.31
    POSITIVE LOGITS
     wheel
    2.33
     Wheel
    2.00
    Wheel
    1.86
    wheel
    1.84
    轮
    1.37
     WHE
    1.32
    輪
    1.26
    휠
    1.18
     rueda
    1.13
    ホイール
    1.12
    Activations Density 0.001%

    No Known Activations