© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260818
    Prev
    Next
    INDEX
    Explanations

    time and space complexity

    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_22_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
     段
    0.48
     paquetes
    0.47
     outlay
    0.46
     expon
    0.45
    气
    0.45
     nici
    0.44
     흰
    0.44
    _{(\
    0.42
    وانات
    0.42
     Burs
    0.42
    POSITIVE LOGITS
    Germany
    0.46
     কাজী
    0.44
     France
    0.44
     Кы
    0.41
    Nazi
    0.40
    ۲۰
    0.40
     Germany
    0.39
     Spain
    0.39
    an
    0.39
    expect
    0.39
    Activations Density 0.000%

    No Known Activations