© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26977
    Prev
    Next
    INDEX
    Explanations

    how to use or run

    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_10_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
    P
    0.39
     as
    0.36
    N
    0.34
    R
    0.34
    B
    0.33
     f
    0.33
     in
    0.32
     brethren
    0.32
    C
    0.30
     up
    0.30
    POSITIVE LOGITS
    nea
    0.29
    いました
    0.29
     আমাকে
    0.28
    ários
    0.27
    izarre
    0.27
     цього
    0.27
    amar
    0.26
    वाड़ा
    0.26
    ください
    0.26
    amaks
    0.26
    Activations Density 0.109%

    No Known Activations