© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38582
    Prev
    Next
    INDEX
    Explanations

    change or unchanged

    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_11_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
    I
    0.67
    E
    0.66
    Fifty
    0.64
    三十
    0.61
    y
    0.61
    Blood
    0.61
    
    0.59
    PAC
    0.58
    n
    0.58
    nader
    0.58
    POSITIVE LOGITS
    ขึ้น
    0.55
     Parisian
    0.54
    お客様
    0.52
    した
    0.50
     up
    0.49
    起来
    0.48
     kao
    0.47
    സ്‌
    0.47
    ตอนนี้
    0.47
     homeomorphic
    0.47
    Activations Density 0.001%

    No Known Activations