© 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. 32892
    Prev
    Next
    INDEX
    Explanations

    utility functions / helpers

    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
    Measurements
    0.33
    ixel
    0.32
     privilegi
    0.32
     treasure
    0.32
    ссив
    0.32
    treasure
    0.32
    ⟣
    0.31
    ᐢ
    0.31
    纶
    0.31
     sf
    0.30
    POSITIVE LOGITS
    嚀
    0.40
     helper
    0.37
     Helper
    0.36
     Helpers
    0.35
     auxiliary
    0.35
     brilliant
    0.34
     utility
    0.34
     सहायक
    0.33
     helpers
    0.33
     assisting
    0.33
    Activations Density 0.002%

    No Known Activations