© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121563
    Prev
    Next
    INDEX
    Explanations

    centralized

    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_38_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
     centralization
    0.54
     central
    0.53
    central
    0.53
     centralised
    0.51
     centralized
    0.50
    >→</
    0.46
     центра
    0.45
     centrally
    0.44
    中央
    0.42
     কেন্দ্রীয়
    0.42
    POSITIVE LOGITS
     επικ
    0.39
    ตรวจ
    0.37
    സ്റ്റി
    0.37
    찍
    0.36
    roskop
    0.36
     Carbide
    0.34
     беспо
    0.34
    産の
    0.34
     benthic
    0.33
    abin
    0.33
    Activations Density 0.006%

    No Known Activations