© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212580
    Prev
    Next
    INDEX
    Explanations

    theology, theocratic, oligarchy

    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_5_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
    '
    1.82
    ق
    1.07
    ग्विजय
    0.99
    తో
    0.98
    ಕ್
    0.95
    D
    0.93
    ح
    0.92
    ش
    0.90
    ר
    0.89
    .'
    0.88
    POSITIVE LOGITS
    s
    1.30
    ем
    1.29
    ى
    1.28
    y
    1.25
    p
    1.21
    el
    1.17
    </span>
    1.11
    т
    1.10
    </code>
    1.09
    z
    1.09
    Activations Density 0.000%

    No Known Activations