© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5926
    Prev
    Next
    INDEX
    Explanations

    AutoModel, AutoTokenizer

    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
    श्वर
    0.38
    是非
    0.38
     ;{
    0.38
     clicar
    0.37
    ATHER
    0.37
    鎸
    0.36
    okhlov
    0.35
    endaftaran
    0.35
    ອີ
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.35
    POSITIVE LOGITS
     prolific
    0.66
     productivity
    0.63
    productivity
    0.61
     prol
    0.57
     productive
    0.57
     Productivity
    0.56
    productive
    0.54
    Prol
    0.54
     productividad
    0.53
     fecund
    0.50
    Activations Density 0.012%

    No Known Activations