© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4690
    Prev
    Next
    INDEX
    Explanations

    the word "table" and surrounding words, especially in a programming context

    oai_token-act-pair · gemini-2.0-flash

    HTML and data tables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     table
    -3.25
     tables
    -3.09
     Table
    -3.05
     Tables
    -2.84
    Table
    -2.84
    table
    -2.75
     TABLE
    -2.70
    TABLE
    -2.64
    Tables
    -2.52
    tables
    -2.48
    POSITIVE LOGITS
     héro
    0.61
     oprot
    0.51
    Datuak
    0.47
    PreferredItem
    0.43
     khởi
    0.43
     hero
    0.43
    LocalizedString
    0.43
     INTERESAR
    0.43
     maaf
    0.42
     CHtml
    0.42
    Activations Density 3.614%

    No Known Activations