© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12386
    Prev
    Next
    INDEX
    Explanations

    问题，答案，选择

    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_40_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
    嗎
    0.45
    吗
    0.41
    了嗎
    0.38
    인가
    0.36
    否
    0.35
    のでしょうか
    0.34
    レン
    0.32
    ไหม
    0.31
    クラ
    0.31
     ли
    0.31
    POSITIVE LOGITS
     oleh
    0.35
     schl
    0.35
    workflow
    0.34
     Pray
    0.34
     Есть
    0.34
    ♐
    0.34
     Fonda
    0.34
     architet
    0.33
     eran
    0.33
     workflow
    0.33
    Activations Density 0.017%

    No Known Activations