© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80790
    Prev
    Next
    INDEX
    Explanations

    agreement or terms

    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_29_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
     Gemüse
    0.50
     Θ
    0.40
    ຜ
    0.40
     Flooring
    0.39
     Ü
    0.38
     விஞ்ஞான
    0.38
    Ejercicio
    0.38
     Dict
    0.38
    剧
    0.38
     Pfl
    0.37
    POSITIVE LOGITS
     كانت
    0.38
    atenated
    0.37
     fast
    0.35
    臺灣
    0.32
     متحد
    0.32
    컨
    0.32
    ably
    0.32
    ichtigung
    0.32
    يال
    0.31
     whereupon
    0.31
    Activations Density 0.001%

    No Known Activations