© 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. 36470
    Prev
    Next
    INDEX
    Explanations

    state-sponsored programs and law

    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
    s
    0.98
    س
    0.91
    स
    0.82
    la
    0.77
    a
    0.77
    covariant
    0.72
    V
    0.71
    ار
    0.69
    d
    0.68
    filament
    0.66
    POSITIVE LOGITS
    0.72
     você
    0.68
    什么
    0.67
     aparelho
    0.64
     you
    0.62
     servizio
    0.62
    คุณ
    0.61
     reação
    0.60
     comércio
    0.59
    大
    0.59
    Activations Density 0.012%

    No Known Activations