© 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. 19696
    Prev
    Next
    INDEX
    Explanations

    you think

    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
     denominado
    0.14
     Cud
    0.14
    氶
    0.14
     Unternehmen
    0.14
    欄
    0.13
     carcinogenesis
    0.13
     賞
    0.13
    ﹁
    0.13
    maßen
    0.13
     chiamato
    0.13
    POSITIVE LOGITS
     نسخة
    0.16
    Invalid
    0.14
    at
    0.14
    iat
    0.14
    iate
    0.14
     luxe
    0.13
     გადა
    0.13
    ri
    0.13
     pays
    0.13
    ies
    0.13
    Activations Density 0.017%

    No Known Activations