© 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. 36486
    Prev
    Next
    INDEX
    Explanations

    even more

    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
     Тут
    0.70
     Дар
    0.66
     Гар
    0.64
     시간이
    0.63
     Але
    0.61
     한
    0.60
     Тому
    0.59
     ,"
    0.58
     Джей
    0.58
     Хан
    0.58
    POSITIVE LOGITS
    s
    0.64
    」。
    0.60
     breakout
    0.57
    ne
    0.54
     lá
    0.53
    用品
    0.53
    x
    0.53
     markt
    0.52
    な
    0.52
    ació
    0.52
    Activations Density 0.023%

    No Known Activations