© 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. 41121
    Prev
    Next
    INDEX
    Explanations

    Quorum, Quora, Quran

    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
    は
    0.96
    是
    0.80
    ۔
    0.78
    ።
    0.77
    は約
    0.75
    тел
    0.73
    는
    0.72
    ع
    0.68
    ના
    0.67
    علي
    0.66
    POSITIVE LOGITS
    t
    0.77
     so
    0.67
    taker
    0.61
    tım
    0.59
    N
    0.59
     west
    0.57
    FH
    0.57
     quorum
    0.57
     such
    0.56
    een
    0.55
    Activations Density 0.008%

    No Known Activations