© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88618
    Prev
    Next
    INDEX
    Explanations

    ส่งผลกระทบ

    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_3_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
    in
    1.05
    ת
    0.87
    տ
    0.75
    ar
    0.70
    ต
    0.70
    ों
    0.69
    send
    0.68
    u
    0.68
    n
    0.68
    터
    0.68
    POSITIVE LOGITS
    (
    0.68
     ර
    0.64
    ;
    0.64
    owymi
    0.63
    ową
    0.61
    owali
    0.60
    ﻒ
    0.60
    owi
    0.59
     বা
    0.58
    Albums
    0.56
    Activations Density 0.001%

    No Known Activations