© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28897
    Prev
    Next
    INDEX
    Explanations

    Ford Mustang

    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_10_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
    ت
    0.85
    );
    0.76
    ，
    0.74
    ي
    0.74
    י
    0.73
    ];
    0.71
    تح
    0.71
    ש
    0.70
    i
    0.69
    З
    0.68
    POSITIVE LOGITS
    mong
    0.72
    mitted
    0.69
    surfing
    0.66
    afar
    0.66
    mäßig
    0.65
    ettle
    0.64
    malt
    0.64
    ede
    0.63
    alım
    0.63
    idos
    0.63
    Activations Density 0.000%

    No Known Activations