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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8522
    Prev
    Next
    INDEX
    Explanations

    structured data, especially with table and field names, and contact form-related terms.

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "first"

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

    Name parts

    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
     незавершена
    -0.85
    WebElementEntity
    -0.75
    protoimpl
    -0.69
     snippetHide
    -0.68
    AutoField
    -0.67
    adaptiveStyles
    -0.66
    TagMode
    -0.64
     kaarangay
    -0.62
    principalColumn
    -0.62
     defaultstate
    -0.61
    POSITIVE LOGITS
    first
    0.63
     first
    0.62
    runApp
    0.60
     middle
    0.52
    First
    0.50
     первый
    0.48
     primeiro
    0.48
     first
    0.47
     password
    0.47
     första
    0.46
    Activations Density 1.433%

    No Known Activations