© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7005
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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_40_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
     eseguire
    0.35
    `).
    0.32
     ejecución
    0.31
    执行
    0.30
     执行
    0.30
     execute
    0.30
     ejecuta
    0.30
     Verde
    0.29
     neutral
    0.29
     chạy
    0.29
    POSITIVE LOGITS
    倭
    0.31
    moss
    0.30
    埬
    0.30
    㶲
    0.30
     mentorship
    0.30
     पीड़
    0.29
    ⨔
    0.29
    Fil
    0.29
    プロジェクト
    0.29
     Ours
    0.28
    Activations Density 0.016%

    No Known Activations