© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88704
    Prev
    Next
    INDEX
    Explanations

    computational fluid dynamics

    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_3_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
    et
    1.00
    t
    0.96
    л
    0.95
    o
    0.94
    es
    0.91
    ž
    0.89
    ل
    0.81
    osť
    0.75
    ت
    0.74
    os
    0.73
    POSITIVE LOGITS
    1
    0.79
     Ці
    0.76
     Цуки
    0.72
     Націона
    0.68
    MktCap
    0.68
     Вікі
    0.67
    ﻣ
    0.66
     Мен
    0.66
     Викто
    0.66
     Балтбет
    0.65
    Activations Density 0.003%

    No Known Activations