© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43144
    Prev
    Next
    INDEX
    Explanations

    machine operation and safety

    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
    マップ
    0.64
    ﻗ
    0.62
     mjesto
    0.57
    _
    0.57
    ي
    0.57
     ي
    0.54
    ﺟ
    0.54
     ম
    0.54
     Kuh
    0.53
     هاي
    0.52
    POSITIVE LOGITS
    陆续
    0.51
    an
    0.50
    一台
    0.50
    同一个
    0.48
    大型
    0.48
    læ
    0.46
     AUC
    0.46
    没有任何
    0.46
     especific
    0.46
    LAND
    0.46
    Activations Density 0.066%

    No Known Activations