© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1503
    Prev
    Next
    INDEX
    Explanations

    precise, uniform, repeatable

    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_39_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
     limit
    0.49
    Limit
    0.47
    limit
    0.42
    絞
    0.42
     практи
    0.39
    Jay
    0.39
    LIMIT
    0.38
    限
    0.38
    撗
    0.38
     Limit
    0.38
    POSITIVE LOGITS
     repeatable
    0.58
     precise
    0.57
     uniform
    0.56
    Uniform
    0.55
     reproducible
    0.54
     repeatability
    0.54
     Uniform
    0.52
     reproducibility
    0.51
     Repeat
    0.50
    精准
    0.50
    Activations Density 0.075%

    No Known Activations