© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49877
    Prev
    Next
    INDEX
    Explanations

    dialogue start

    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
    frame
    0.35
     წარ
    0.33
    netje
    0.33
    ikka
    0.33
    imageList
    0.33
    畑
    0.33
    そ
    0.32
    etail
    0.32
    viewport
    0.31
    =%
    0.31
    POSITIVE LOGITS
     utilities
    0.43
     Utilities
    0.41
    Rourke
    0.38
    Attractive
    0.37
     kilogram
    0.37
    Utilities
    0.36
     acer
    0.36
    夥
    0.36
     alab
    0.36
     glassware
    0.36
    Activations Density 0.001%

    No Known Activations