© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88016
    Prev
    Next
    INDEX
    Explanations

    William the Conqueror

    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
    ला
    0.69
    f
    0.67
    ्याज
    0.66
    ج
    0.66
    ص
    0.66
    </h2>
    0.62
    </h3>
    0.62
    ما
    0.62
    ai
    0.61
    ном
    0.61
    POSITIVE LOGITS
     كبير
    0.65
     stessi
    0.56
    ,
    0.56
    rü
    0.55
    つける
    0.55
     übertragen
    0.54
     persoane
    0.54
     peu
    0.54
     leichter
    0.53
    Kalb
    0.52
    Activations Density 0.000%

    No Known Activations