© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199309
    Prev
    Next
    INDEX
    Explanations

    rhombus, diamond, dolomite

    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
    Not in Any Lists

    No Comments

    Negative Logits
    дей
    0.55
    ニー
    0.52
    欲
    0.52
     désir
    0.50
    用
    0.49
    اي
    0.49
    ત્રી
    0.49
    卻
    0.48
    理
    0.48
    ر
    0.48
    POSITIVE LOGITS
     Tat
    0.62
     Tuberculosis
    0.59
    ams
    0.57
    kswagen
    0.57
     Thackeray
    0.55
     हंस
    0.55
     Lakeland
    0.55
    uberculosis
    0.54
     Tiwari
    0.53
     Ку
    0.52
    Activations Density 0.000%

    No Known Activations