© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139888
    Prev
    Next
    INDEX
    Explanations

    sports

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Mac
    0.39
    Grid
    0.39
    knot
    0.39
    Ho
    0.38
    ཆ
    0.38
     ..............
    0.37
    Nation
    0.37
    强化
    0.36
     czter
    0.36
    Global
    0.36
    POSITIVE LOGITS
     تیاری
    0.48
    DATAS
    0.46
     spring
    0.45
     কু
    0.43
    荠
    0.43
     الرب
    0.43
     keuken
    0.43
    BRUARY
    0.42
     봄
    0.41
     breakup
    0.39
    Activations Density 0.000%

    No Known Activations