© 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. 29958
    Prev
    Next
    INDEX
    Explanations

    core banking financial terms

    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
     слад
    0.39
    ClassLoader
    0.38
     सोड
    0.38
    Swing
    0.38
    镭
    0.37
    TypeOf
    0.37
    Ev
    0.36
     कोटा
    0.36
    幅
    0.35
    ذی
    0.35
    POSITIVE LOGITS
     banking
    0.76
     Banking
    0.68
    Banking
    0.67
     bank
    0.64
    banking
    0.63
     banker
    0.60
     банков
    0.60
     banks
    0.59
     banque
    0.56
    bank
    0.55
    Activations Density 0.036%

    No Known Activations