© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119818
    Prev
    Next
    INDEX
    Explanations

    ```pythonclass

    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_27_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
    exploration
    0.38
     탐
    0.38
    ingo
    0.38
    탐
    0.37
    来て
    0.37
    trying
    0.36
    iPad
    0.36
     detr
    0.36
    وتر
    0.36
     тка
    0.35
    POSITIVE LOGITS
     previews
    0.43
     APIs
    0.41
    ῴ
    0.40
    ensibly
    0.38
     breezes
    0.38
     Database
    0.38
     screenshots
    0.37
    (/*
    0.37
     Datenbank
    0.37
     Lyn
    0.37
    Activations Density 0.000%

    No Known Activations