© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44223
    Prev
    Next
    INDEX
    Explanations

    COUNT, SUM, IF, Function

    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_13_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
    代わりに
    0.53
    IMA
    0.50
    较高的
    0.49
    нути
    0.48
    0.48
    考えると
    0.48
    <h4>
    0.47
    Aer
    0.47
     ，
    0.47
    Tony
    0.47
    POSITIVE LOGITS
     lás
    0.55
    ally
    0.52
     renin
    0.51
     tí
    0.50
    inson
    0.50
     satin
    0.49
     بزر
    0.49
     osk
    0.49
    iskup
    0.49
     naran
    0.49
    Activations Density 0.011%

    No Known Activations