© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46392
    Prev
    Next
    INDEX
    Explanations

    ```csharpusing```

    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_13_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
    a
    0.18
    े
    0.17
     ने
    0.16
    隷
    0.16
    오
    0.16
    په
    0.15
    งาม
    0.15
    아이
    0.14
    엔
    0.14
    டன்
    0.14
    POSITIVE LOGITS
     market
    0.17
    maları
    0.17
    郏
    0.17
     на
    0.17
     точка
    0.17
     ሽፋን
    0.17
     పథ
    0.17
     प्रमाणात
    0.17
    市场
    0.17
    mäßig
    0.17
    Activations Density 0.001%

    No Known Activations