© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8257
    Prev
    Next
    INDEX
    Explanations

    words related to sales, discounts, returns and retail

    oai_token-act-pair · gemini-2.0-flash

    stock

    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
    BeginContext
    -0.56
    cagon
    -0.50
    delwed
    -0.49
    칙
    -0.49
    цездатний
    -0.48
    ulsions
    -0.47
    conceito
    -0.47
    দ্ধ
    -0.47
    rrggbb
    -0.46
    AndEndTag
    -0.46
    POSITIVE LOGITS
     stock
    1.95
    stock
    1.70
    Stock
    1.66
     STOCK
    1.59
     Stock
    1.56
    STOCK
    1.48
    stocks
    1.27
     stocks
    1.21
     Stocks
    1.08
    Stocks
    0.95
    Activations Density 6.841%

    No Known Activations