© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99253
    Prev
    Next
    INDEX
    Explanations

    minister and ministry titles

    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_14_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
     యా
    0.31
     બનાવવા
    0.31
    𝐮
    0.30
    ουν
    0.29
     করিল
    0.29
     ду
    0.28
    outi
    0.28
     ピン
    0.28
    ξη
    0.27
     نیز
    0.27
    POSITIVE LOGITS
    Minister
    0.34
    ministerium
    0.32
     ministerio
    0.31
    Minist
    0.30
     Minister
    0.29
    ت
    0.29
    मंत्र
    0.29
     Truth
    0.28
    os
    0.27
     ministro
    0.27
    Activations Density 0.001%

    No Known Activations