© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78882
    Prev
    Next
    INDEX
    Explanations

    instructions to run code

    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_31_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
    amas
    0.37
    `;
    0.36
    ungi
    0.36
     muka
    0.36
     først
    0.36
     ogr
    0.35
     Mani
    0.35
    ';
    0.35
    ogy
    0.35
     aminoglycos
    0.35
    POSITIVE LOGITS
     півні
    0.45
    ೊಂದಿಗೆ
    0.42
    NavController
    0.39
     Nä
    0.39
     داخل
    0.38
     ओळख
    0.38
    ⁢
    0.38
     ಯಾವುದೇ
    0.37
     Ekim
    0.37
    Ŋ
    0.37
    Activations Density 0.001%

    No Known Activations