© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39662
    Prev
    Next
    INDEX
    Explanations

    share buybacks

    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_3_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
    ü
    0.80
    ire
    0.74
    c
    0.73
     sicuro
    0.70
    би
    0.64
     condiv
    0.64
     It
    0.63
     lý
    0.63
    v
    0.62
    ма
    0.62
    POSITIVE LOGITS
    ص
    0.75
    تون
    0.75
    س
    0.73
    تان
    0.73
    </h1>
    0.70
    র
    0.70
    ب
    0.70
    </h3>
    0.69
    </h2>
    0.66
    </h4>
    0.65
    Activations Density 0.015%

    No Known Activations