© 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. 35663
    Prev
    Next
    INDEX
    Explanations

    group strategies

    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
     Бе
    0.56
    Ди
    0.56
    5
    0.55
    ?")
    0.55
     Вообще
    0.55
    かれた
    0.54
     guzt
    0.54
    Council
    0.53
    チャ
    0.52
    挙げ
    0.52
    POSITIVE LOGITS
    et
    0.61
    as
    0.61
     invariable
    0.56
    mith
    0.54
     absol
    0.54
    స్‌
    0.54
    ن
    0.54
    ก
    0.54
    ่อ
    0.53
    🆈
    0.53
    Activations Density 0.007%

    No Known Activations