© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199502
    Prev
    Next
    INDEX
    Explanations

    bureaucratic

    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_9_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
    ↵
    0.43
    ta
    0.41
    ى
    0.40
    сей
    0.39
    к
    0.39
    ре
    0.37
    want
    0.37
    3
    0.36
    рина
    0.35
    <0xBB>
    0.35
    POSITIVE LOGITS
    ৯
    0.53
    ہ
    0.49
    é
    0.48
    과
    0.46
    a
    0.46
    ist
    0.45
    スナー
    0.45
    ası
    0.43
    យើង
    0.43
    이
    0.43
    Activations Density 0.001%

    No Known Activations