© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11864
    Prev
    Next
    INDEX
    Explanations

    a collection of seemingly disparate concepts, including coding elements, gambling-related terms, names and numbers

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     تانيه
    -0.60
    KELEY
    -0.55
    extAlignment
    -0.55
    !*\
    -0.54
    estroy
    -0.54
     تضيفلها
    -0.53
    ereza
    -0.53
    WriteBarrier
    -0.53
     Cataloging
    -0.50
     particular
    -0.49
    POSITIVE LOGITS
    脚注の使い方
    0.62
     Paglinawan
    0.58
     iconTwitter
    0.56
     gynhyrchwyd
    0.56
    retweeted
    0.55
     ویکی‌پدیا
    0.53
     dieux
    0.50
     Richelieu
    0.49
    hastly
    0.47
     refirió
    0.47
    Activations Density 0.260%

    No Known Activations