© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164747
    Prev
    Next
    INDEX
    Explanations

    king, kingdom, duke, doge

    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
     Lille
    0.42
    辐射
    0.39
     नृत्य
    0.39
    㧔
    0.38
     مُعرِّف
    0.37
     द्रव
    0.36
    𝔰
    0.36
     关于
    0.36
    ्ले
    0.36
     ისინი
    0.36
    POSITIVE LOGITS
     Magna
    0.38
     aliado
    0.37
    hi
    0.34
     тысячи
    0.33
    anjay
    0.33
     arrays
    0.33
    చి
    0.33
     annih
    0.33
     Esqu
    0.33
     alun
    0.33
    Activations Density 0.001%

    No Known Activations