© 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. 6422
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and commas within those dollar amounts

    oai_token-act-pair · gemini-2.0-flash

    numerical values and currency symbols

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

    Monetary amounts

    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
     million
    -0.68
     milhões
    -0.64
     millions
    -0.63
     millones
    -0.59
     milioni
    -0.57
    一百
    -0.56
     miljoen
    -0.52
     crore
    -0.52
    millions
    -0.51
    VersionUID
    -0.50
    POSITIVE LOGITS
     thousand
    0.74
     يتيمه
    0.64
    thou
    0.62
     thousands
    0.62
    thousand
    0.62
     محفوظة
    0.61
    thousands
    0.61
     Egli
    0.61
     صوتيه
    0.60
    =$?
    0.60
    Activations Density 0.212%

    No Known Activations