© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144421
    Prev
    Next
    INDEX
    Explanations

    psychomotor and policy

    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_0_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
    af
    1.79
    ac
    1.73
    ana
    1.70
     (
    1.66
     are
    1.63
    ara
    1.59
    ach
    1.43
    el
    1.42
    fe
    1.38
    ian
    1.34
    POSITIVE LOGITS
    د
    2.08
    ب
    1.81
    ش
    1.74
    มัน
    1.62
    其他
    1.57
    ز
    1.52
    ل
    1.46
    سی
    1.41
    م
    1.39
    ו
    1.39
    Activations Density 0.001%

    No Known Activations