© 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. 43640
    Prev
    Next
    INDEX
    Explanations

    Mad Max: Fury Road

    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
    k
    0.93
    ية
    0.91
    ARA
    0.74
    ي
    0.73
    ᚕ
    0.73
    i
    0.72
     രീതി
    0.71
    ک
    0.71
    sG
    0.70
     in
    0.69
    POSITIVE LOGITS
    ung
    0.92
    ام
    0.84
    ل
    0.79
    ज
    0.78
    ला
    0.73
    ang
    0.72
    ード
    0.71
    م
    0.70
    ب
    0.68
    ę
    0.67
    Activations Density 0.000%

    No Known Activations