© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111225
    Prev
    Next
    INDEX
    Explanations

    Thucydides Trap

    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_2_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
    و
    1.95
    ب
    1.84
    م
    1.79
    ا
    1.70
    ו
    1.67
    ان
    1.64
    м
    1.59
    다
    1.58
    ры
    1.50
    י
    1.49
    POSITIVE LOGITS
    v
    1.16
    ’
    1.13
    '
    1.12
    c
    1.10
    ill
    1.07
    oo
    1.01
    ooo
    1.01
     for
    0.98
    $
    0.98
    x
    0.95
    Activations Density 0.000%

    No Known Activations