© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91891
    Prev
    Next
    INDEX
    Explanations

    Belgian, Lens, Belgium, Congo, Revolution

    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_11_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
    اس
    0.57
    اد
    0.54
    <0xB3>
    0.53
    ToString
    0.51
    os
    0.50
     も
    0.49
    all
    0.48
     )(
    0.48
    WHEN
    0.47
     फ्रॉम
    0.46
    POSITIVE LOGITS
     impede
    0.55
     swoop
    0.55
     hydrogen
    0.51
     Δ
    0.50
     relocate
    0.49
     communications
    0.48
     prerog
    0.48
     rulemaking
    0.48
     gentle
    0.47
    icarbon
    0.47
    Activations Density 0.002%

    No Known Activations