© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247479
    Prev
    Next
    INDEX
    Explanations

    wheel, hub, inch

    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_40_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
    碰撞
    0.41
     Realms
    0.41
     colliding
    0.40
     Tind
    0.40
    Tiles
    0.38
     paint
    0.37
     கண்ணாடி
    0.37
    PAINT
    0.37
    Paint
    0.36
    Ử
    0.36
    POSITIVE LOGITS
     shawl
    0.40
     आओ
    0.39
     Problem
    0.39
     Parameters
    0.38
    acharya
    0.38
    pecia
    0.37
     oms
    0.37
     lightweight
    0.37
    อา
    0.37
     lightness
    0.36
    Activations Density 0.000%

    No Known Activations