© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194284
    Prev
    Next
    INDEX
    Explanations

    Bostrom and simulation

    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_4_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
    it
    1.09
    ร
    1.08
    ו
    1.06
    ro
    1.01
    اب
    1.01
    ح
    1.00
    ین
    0.98
    ان
    0.94
    ol
    0.93
    v
    0.91
    POSITIVE LOGITS
    ли
    1.22
     дости
    0.86
    <0x80>
    0.83
    shall
    0.77
    not
    0.77
     приго
    0.72
    у
    0.71
     память
    0.69
     которую
    0.68
     роль
    0.68
    Activations Density 0.000%

    No Known Activations