© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33628
    Prev
    Next
    INDEX
    Explanations

    research and development

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     New
    0.49
    新
    0.44
    New
    0.43
     khấu
    0.40
     NEW
    0.39
    的新
    0.38
     નવી
    0.38
     Consumption
    0.37
     掛け
    0.37
     newcom
    0.36
    POSITIVE LOGITS
    __."
    0.37
    Ele
    0.36
    Element
    0.35
    ื่อ
    0.34
    èle
    0.33
    teman
    0.33
     ஆரோ
    0.33
    эле
    0.33
    ᡳ
    0.33
    ເວ
    0.33
    Activations Density 0.012%

    No Known Activations