© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15204
    Prev
    Next
    INDEX
    Explanations

    travel writing, blogs, and adventure gear

    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_13_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
    सभी
    0.47
     bacterias
    0.43
     ordenar
    0.42
    포
    0.42
    yección
    0.42
    ຈັດສົ່ງ
    0.41
     recib
    0.41
     todas
    0.41
    ώσει
    0.41
    туа
    0.41
    POSITIVE LOGITS
     ファッション
    0.48
     ભા
    0.46
     Scully
    0.46
     Sicher
    0.45
     فرض
    0.45
     транспорт
    0.45
     montagne
    0.45
     Powers
    0.44
     з
    0.42
     سید
    0.42
    Activations Density 0.029%

    No Known Activations