© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48490
    Prev
    Next
    INDEX
    Explanations

    cited as

    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_10_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
    ↵↵
    0.78
     Denne
    0.77
    }",
    0.73
     as
    0.72
     CASA
    0.70
     Montague
    0.68
    ”,
    0.68
    }-\
    0.67
     Stelle
    0.66
     NDP
    0.66
    POSITIVE LOGITS
    퐫
    0.80
    れる
    0.79
    <0x80>
    0.76
    کم
    0.75
    i
    0.75
    و
    0.75
    ми
    0.73
    them
    0.72
    𝕚
    0.72
    𝗮
    0.70
    Activations Density 0.002%

    No Known Activations