© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165442
    Prev
    Next
    INDEX
    Explanations

    strategy

    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_31_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
     宋
    0.39
    炬
    0.36
     میک
    0.35
     وکړئ
    0.35
    GetOffset
    0.34
    යට
    0.34
    籾
    0.33
    宋
    0.33
    防止
    0.33
    铧
    0.33
    POSITIVE LOGITS
     Strategy
    0.55
     strategy
    0.55
     strategies
    0.53
     estratégia
    0.51
     страте
    0.50
    strateg
    0.50
    Strategy
    0.49
     stratég
    0.49
     gameplay
    0.48
     전략
    0.48
    Activations Density 0.003%

    No Known Activations