© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35357
    Prev
    Next
    INDEX
    Explanations

    cards, Dota, payments

    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_11_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
    رفت
    0.63
     Ре
    0.56
    TRI
    0.55
    пус
    0.55
    昆
    0.53
    ене
    0.52
     الثانوي
    0.52
    述
    0.52
    Perf
    0.52
    áus
    0.52
    POSITIVE LOGITS
     извест
    0.65
     नितिन
    0.63
     причиной
    0.60
    ถนน
    0.58
    ร้อม
    0.57
     причины
    0.56
    nite
    0.55
     available
    0.54
     yalnızca
    0.54
     обычной
    0.54
    Activations Density 0.001%

    No Known Activations