© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43624
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     Requirements
    0.49
     राज्यपाल
    0.46
     Parlamento
    0.46
     requisito
    0.46
     tz
    0.45
     leit
    0.44
     tt
    0.44
    稞
    0.43
    高品質
    0.43
     Postgraduate
    0.43
    POSITIVE LOGITS
    د
    0.56
    شي
    0.52
    م
    0.51
    ام
    0.50
     indexes
    0.50
    ن
    0.50
     officers
    0.48
     discharges
    0.48
    er
    0.48
    vectors
    0.45
    Activations Density 0.000%

    No Known Activations