© 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. 12343
    Prev
    Next
    INDEX
    Explanations

    numerical values related to currency or large quantities

    oai_token-act-pair · gemini-2.0-flash

    words related to large quantities or amounts

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

    Millions

    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
     thousand
    -0.85
    thou
    -0.75
     thou
    -0.70
     thousands
    -0.69
    thousand
    -0.69
     يتيمه
    -0.67
     Thousand
    -0.64
     thous
    -0.63
     THOUS
    -0.61
    thousands
    -0.58
    POSITIVE LOGITS
    一百
    0.59
     protoimpl
    0.57
    EReference
    0.56
     milhões
    0.55
    VersionUID
    0.53
     millions
    0.53
    SuppressMessage
    0.52
     OMITBAD
    0.52
     الرياضيه
    0.52
     nahilalakip
    0.50
    Activations Density 0.853%

    No Known Activations