© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208492
    Prev
    Next
    INDEX
    Explanations

    python todos

    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_25_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
    ざ
    0.39
     Biz
    0.38
     παρά
    0.37
    やか
    0.37
     მაგრამ
    0.37
     lekin
    0.37
     Kait
    0.37
     ፓ
    0.37
     ラ
    0.36
    لیکن
    0.36
    POSITIVE LOGITS
    管理局
    0.37
     மாநிலத்தில்
    0.37
    Cao
    0.36
    ‍ह
    0.35
    colored
    0.34
    ভারতের
    0.33
     최초
    0.33
     প্রথমবারের
    0.32
    铝
    0.32
     میلیون
    0.32
    Activations Density 0.002%

    No Known Activations