© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1598
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    attributes and tags in HTML

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

    code snippets and documentation

    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
    Negative Logits
     scolaire
    -0.67
     Económica
    -0.65
     Othello
    -0.65
     JAXBElement
    -0.64
     financière
    -0.63
     juridiques
    -0.62
     OTO
    -0.62
    ρών
    -0.62
     fundus
    -0.62
     Chinatown
    -0.61
    POSITIVE LOGITS
    IsContent
    0.55
    Bronnen
    0.42
    MemoryWarning
    0.41
     estekak
    0.39
    FOLK
    0.38
    HtmlAttribute
    0.37
    ">//
    0.37
    parsedMessage
    0.37
     CreateTagHelper
    0.37
    readystatechange
    0.36
    Activations Density 1.092%

    No Known Activations