© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 24291
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ↵↵↵↵
    0.82
    ↵↵↵
    0.74
    ↵↵↵↵↵
    0.69
    ))).
    0.61
    ])).
    0.59
    "]));
    0.59
    ']));
    0.55
    ())));
    0.54
    ())))
    0.52
    )]);
    0.52
    POSITIVE LOGITS
    '){
    0.38
    <h5>
    0.38
    參與
    0.38
     выяв
    0.36
    "){
    0.36
    ]{\
    0.35
    <0x0C>
    0.35
    #######
    0.34
    }]{
    0.34
     जीवन
    0.34
    Activations Density 0.021%

    No Known Activations