© 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. 89637
    Prev
    Next
    INDEX
    Explanations

    Flaviviridae, flavanols, virus-related

    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
    ди
    0.63
    shaped
    0.59
    s
    0.59
    (())
    0.57
    й
    0.57
    is
    0.56
    ಂಗ್ರೆ
    0.56
    ம்
    0.56
     cải
    0.55
    down
    0.55
    POSITIVE LOGITS
    ل
    0.76
    PP
    0.67
    <0x0D>
    0.66
    IA
    0.64
    ל
    0.63
    ك
    0.62
    og
    0.61
    不是
    0.61
    RP
    0.59
    SK
    0.59
    Activations Density 0.001%

    No Known Activations