© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24890
    Prev
    Next
    INDEX
    Explanations

    revolutionize, revolutionize, revolution

    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
    ן
    0.80
    ס
    0.72
    是
    0.71
    نا
    0.68
    К
    0.64
     gratuit
    0.63
    ;
    0.62
    는
    0.61
     gratu
    0.61
    [
    0.60
    POSITIVE LOGITS
     revolution
    0.84
     Revolution
    0.83
    revolution
    0.82
     revolutionize
    0.80
    Revolution
    0.77
     револю
    0.75
     revolución
    0.73
     Meade
    0.70
    CCESS
    0.64
    糹
    0.64
    Activations Density 0.026%

    No Known Activations