© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115478
    Prev
    Next
    INDEX
    Explanations

    scheduling updates

    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
    downloads
    0.41
    的最佳
    0.39
    冠军
    0.39
    ago
    0.38
     downloads
    0.38
    ╅
    0.37
     Bruce
    0.37
     BSTC
    0.37
    enged
    0.36
     Thunder
    0.36
    POSITIVE LOGITS
     redux
    0.40
    ഘടന
    0.39
    )];
    0.39
    ذور
    0.39
    )));
    0.37
    ReactDOM
    0.36
     endless
    0.36
     reprend
    0.35
    差
    0.35
     pledge
    0.35
    Activations Density 0.001%

    No Known Activations