© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64901
    Prev
    Next
    INDEX
    Explanations

    invoices and bills

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Сы
    0.38
    铁
    0.37
     taping
    0.37
    াৎ
    0.37
    वुड
    0.36
    ત્મક
    0.36
    hko
    0.36
    錫
    0.36
    Gut
    0.35
    笃
    0.35
    POSITIVE LOGITS
     invoice
    2.31
     invoices
    2.08
     Invoice
    2.03
    invoice
    1.99
    Invoice
    1.95
     bill
    1.80
     bills
    1.74
     invoicing
    1.72
    bills
    1.62
     Bills
    1.55
    Activations Density 0.031%

    No Known Activations