© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53459
    Prev
    Next
    INDEX
    Explanations

    efficiency and optimization

    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_30_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
     Safegu
    0.48
    ⌋
    0.42
    பொ
    0.39
     захи
    0.39
     Уни
    0.39
    iteľ
    0.39
     Badajoz
    0.39
     зага
    0.38
    ╰
    0.38
     Soft
    0.36
    POSITIVE LOGITS
    efficient
    0.50
     efficient
    0.48
     effiz
    0.47
    efficiency
    0.47
    CLASSES
    0.46
    efficiencies
    0.45
     efficiency
    0.45
     효율
    0.45
     efficiencies
    0.45
    效率
    0.43
    Activations Density 0.020%

    No Known Activations