© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51113
    Prev
    Next
    INDEX
    Explanations

    tax codes and numbers

    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_31_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
    税
    0.49
     जीएसटी
    0.47
     Tax
    0.46
     VAT
    0.45
     GST
    0.45
    GST
    0.44
     税
    0.43
     tax
    0.42
    tax
    0.41
    Tax
    0.41
    POSITIVE LOGITS
     vm
    0.47
     VM
    0.41
     calmer
    0.39
     calm
    0.39
     plots
    0.38
    $=\
    0.38
     violent
    0.38
     সহিংস
    0.38
    violent
    0.37
    Hub
    0.37
    Activations Density 0.020%

    No Known Activations