© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124616
    Prev
    Next
    INDEX
    Explanations

    keynote speakers and addresses

    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_37_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
    ﾓ
    0.41
    лән
    0.37
    飘
    0.36
    状态
    0.36
     superintend
    0.35
     ಸ್ಥಳ
    0.34
    肢
    0.34
    装置
    0.34
     மாநக
    0.34
    ≦
    0.34
    POSITIVE LOGITS
    講演
    0.58
    Attendees
    0.58
     attendees
    0.56
    Speaker
    0.53
     attendee
    0.50
     Attendees
    0.50
    讲
    0.49
    Speakers
    0.48
     বক্ত
    0.48
     लेक्चर
    0.48
    Activations Density 0.000%

    No Known Activations