© 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. 56667
    Prev
    Next
    INDEX
    Explanations

    "inse" followed by "curities"

    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
    knife
    0.55
     confided
    0.54
    鰯
    0.53
     규
    0.52
     sombre
    0.51
     ನನಗೆ
    0.51
     ಸಲ
    0.50
     elastomer
    0.50
    xan
    0.50
    ali
    0.48
    POSITIVE LOGITS
    ه‌ها
    0.61
    _
    0.52
    مرات
    0.47
     الماض
    0.45
    сказа
    0.45
    ‌
    0.44
    ه‌
    0.44
    ه‌های
    0.44
    োরে
    0.43
     Prepare
    0.42
    Activations Density 0.000%

    No Known Activations