© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43202
    Prev
    Next
    INDEX
    Explanations

    Artificial General Intelligence

    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
    দিগকে
    0.75
     personas
    0.73
    \
    0.73
    ۴
    0.73
     pastas
    0.70
     pandemics
    0.70
    ۵
    0.70
    ۳
    0.68
     conoscenze
    0.66
     competenze
    0.66
    POSITIVE LOGITS
    ad
    0.90
    a
    0.79
    Intelligence
    0.79
    ن
    0.79
    ?
    0.78
     Intelligence
    0.78
    ه
    0.77
    s
    0.75
    at
    0.73
    um
    0.73
    Activations Density 0.005%

    No Known Activations