© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 9832
    Prev
    Next
    INDEX
    Explanations

    themes

    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_40_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
     Jamal
    0.38
    ໄລ
    0.37
     विज्ञ
    0.37
     Registrar
    0.37
    电视剧
    0.37
     affidavit
    0.37
     Larn
    0.36
    腌
    0.36
    enbach
    0.36
    underset
    0.36
    POSITIVE LOGITS
     themes
    0.91
     Themes
    0.75
     tema
    0.73
    themes
    0.73
    Themes
    0.72
     temas
    0.70
     тема
    0.69
     elements
    0.65
     temática
    0.65
    テーマ
    0.64
    Activations Density 0.380%

    No Known Activations