© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4791
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    Downloading
    0.24
    下載
    0.23
    鎳
    0.23
     下载
    0.23
    ႂ
    0.23
     რა
    0.23
     Downloading
    0.22
    美術館
    0.22
     trastornos
    0.21
    Drinking
    0.21
    POSITIVE LOGITS
     хорошо
    0.24
    inline
    0.24
     inline
    0.24
     ali
    0.23
     Oriental
    0.23
     oriented
    0.22
    ↵↵↵↵↵↵
    0.22
     gan
    0.22
    განი
    0.21
    רות
    0.21
    Activations Density 0.092%

    No Known Activations