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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12090
    Prev
    Next
    INDEX
    Explanations

    words associated with numbers, rates, and financial calculations

    oai_token-act-pair · gemini-2.0-flash

    economics/finance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rates
    -1.93
     rates
    -1.90
     Rate
    -1.84
    Rates
    -1.80
    Rate
    -1.77
     rate
    -1.76
     RATE
    -1.69
     RATES
    -1.63
    rate
    -1.55
    RATE
    -1.52
    POSITIVE LOGITS
     مشارکت‌کنندگان
    0.55
    protoimpl
    0.54
    /*---
    0.53
     bezeichneter
    0.51
     surla
    0.50
    Jegyzetek
    0.49
    paramref
    0.47
    DebuggerNonUser
    0.46
     EconPapers
    0.46
     []:
    0.46
    Activations Density 3.390%

    No Known Activations