© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193808
    Prev
    Next
    INDEX
    Explanations

    lug nuts and quick releases

    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_15_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
     pe
    0.48
     unsightly
    0.48
     malos
    0.48
    かけた
    0.47
     espes
    0.46
     pil
    0.46
    व
    0.46
    luss
    0.46
     kayu
    0.46
     ഏത
    0.46
    POSITIVE LOGITS
    馍
    0.51
    imore
    0.50
     मुहैया
    0.50
     गर्ने
    0.49
    指令
    0.49
     شیع
    0.49
    áln
    0.48
    urno
    0.47
    страницу
    0.47
    ies
    0.47
    Activations Density 0.001%

    No Known Activations