© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15314
    Prev
    Next
    INDEX
    Explanations

    time.deltaTime

    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
    Negative Logits
    irat
    0.58
     w
    0.58
     temperatur
    0.55
    ilat
    0.49
    <0x9F>
    0.49
     name
    0.49
     groundbreaking
    0.49
    il
    0.48
    urer
    0.48
     man
    0.48
    POSITIVE LOGITS
    También
    0.51
    机场
    0.45
    仅
    0.45
    ่ง
    0.44
    底
    0.44
    旬
    0.43
    ス
    0.42
    参考文献
    0.42
    ويم
    0.42
    仕
    0.42
    Activations Density 0.005%

    No Known Activations