© 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-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11920
    Prev
    Next
    INDEX
    Explanations

    words in emails pertaining to commodities exchanges regulated by US agencies

    oai_token-act-pair · gemini-2.0-flash

    commodities and exchanges

    np_token-act-pair-logits · gpt-4o-mini

    exchanges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    日閲覧
    -0.64
    رشف
    -0.62
    aarrggbb
    -0.61
     cherchés
    -0.60
     виправивши
    -0.59
    IVEREF
    -0.59
     المعيارى
    -0.56
    dze
    -0.55
     estimés
    -0.55
     Rugg
    -0.55
    POSITIVE LOGITS
     exchanges
    0.68
     exchange
    0.67
     Exchange
    0.59
    Exchange
    0.58
    exchange
    0.58
     EXCHANGE
    0.56
     Exchanges
    0.55
     légales
    0.54
     regulated
    0.53
    EXCHANGE
    0.53
    Activations Density 1.489%

    No Known Activations