© 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. 4609
    Prev
    Next
    INDEX
    Explanations

    HTML and Javascript code snippets, especially table-related

    oai_token-act-pair · gemini-2.0-flash

    table structure terminology

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

    rows and columns

    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
    SourceChecksum
    -0.81
     initComponents
    -0.62
    ніципалі
    -0.57
    NOPQRST
    -0.56
     esternos
    -0.56
    RetentionPolicy
    -0.55
    BeginInit
    -0.54
     bezeichneter
    -0.52
     estekak
    -0.52
    VersionUID
    -0.52
    POSITIVE LOGITS
     row
    1.89
     columns
    1.77
     column
    1.77
     rows
    1.76
     Row
    1.66
     Columns
    1.57
    Row
    1.55
     Rows
    1.55
     Column
    1.54
    row
    1.53
    Activations Density 7.237%

    No Known Activations