© 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. 44108
    Prev
    Next
    INDEX
    Explanations

    microkernel architecture or management

    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
    art
    0.95
    p
    0.85
    ඨ
    0.84
    ana
    0.84
    '
    0.84
    ac
    0.83
    ik
    0.82
    ann
    0.82
    น
    0.82
    िक
    0.81
    POSITIVE LOGITS
     in
    0.89
     في
    0.81
    لي
    0.79
    在
    0.77
     ιδια
    0.75
    t
    0.75
    في
    0.75
    <0x80>
    0.72
    RIBUT
    0.71
    ه
    0.70
    Activations Density 0.001%

    No Known Activations