© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3400
    Prev
    Next
    INDEX
    Explanations

    layered, multifaceted, holistic, core

    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_39_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
     sAlarm
    0.38
    QUI
    0.38
     Tala
    0.38
    輸
    0.37
    ':'
    0.36
     Springer
    0.36
     Quiet
    0.36
     Persistence
    0.36
     CAT
    0.36
     rss
    0.36
    POSITIVE LOGITS
    றிந்த
    0.38
    ✮
    0.36
    まとめて
    0.36
     philosophical
    0.35
     overhaul
    0.35
     ремонт
    0.35
    Женско
    0.35
     छत्र
    0.34
     betracht
    0.34
     avenue
    0.34
    Activations Density 0.099%

    No Known Activations