© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1905
    Prev
    Next
    INDEX
    Explanations

    笑了起来, laugh, 眯, pleasant surprise

    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_40_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
     kişi
    0.45
     ಬು
    0.43
     रख
    0.42
     ena
    0.41
    ⼈
    0.40
    ཟ
    0.40
     racional
    0.39
    吘
    0.39
     voz
    0.39
     ಜನರು
    0.39
    POSITIVE LOGITS
     Myth
    0.40
    pu
    0.39
     metaphorical
    0.38
    yg
    0.37
    wendungen
    0.36
    wend
    0.36
    Liter
    0.36
    跳
    0.36
    Myth
    0.35
     skimming
    0.35
    Activations Density 0.002%

    No Known Activations