© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136864
    Prev
    Next
    INDEX
    Explanations

    ключевые слова

    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_12_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
     Pflege
    0.59
    し
    0.56
    ల్యే
    0.55
    フルーツ
    0.54
    юм
    0.54
    ధం
    0.54
    れない
    0.53
    りたい
    0.52
     கூடிய
    0.52
    后缀
    0.52
    POSITIVE LOGITS
    نج
    0.57
     cinc
    0.53
    ס
    0.50
     c
    0.48
     croit
    0.48
     cot
    0.47
     vedit
    0.47
     tomo
    0.46
    p
    0.46
     sépt
    0.46
    Activations Density 0.000%

    No Known Activations