© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33280
    Prev
    Next
    INDEX
    Explanations

    features and Benefits

    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_3_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
    IA
    0.70
    是
    0.64
    ing
    0.63
    ING
    0.63
    ంత
    0.62
    ك
    0.59
    .
    0.59
    ت
    0.58
    म
    0.57
    ac
    0.55
    POSITIVE LOGITS
    ی
    0.88
    куп
    0.72
    τή
    0.70
    し
    0.68
    د
    0.65
    ો
    0.64
    шк
    0.63
    異なります
    0.63
     типу
    0.62
    ಿಗಳ
    0.62
    Activations Density 0.034%

    No Known Activations