© 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. 10235
    Prev
    Next
    INDEX
    Explanations

    code snippets that have to do with threads, transactions, mutex locks, and other code related jargon

    oai_token-act-pair · gemini-2.0-flash

    code transactions/locking

    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
     transaction
    -0.55
    transaction
    -0.52
     licencia
    -0.51
    Transaction
    -0.48
    вла
    -0.43
     lez
    -0.43
     petto
    -0.41
    勿
    -0.40
     safe
    -0.40
    cso
    -0.40
    POSITIVE LOGITS
    LookAnd
    0.73
     صوتيه
    0.71
    setVerticalGroup
    0.70
    HtmlAttribute
    0.69
    PerformLayout
    0.68
    BitmapFactory
    0.68
    contentLoaded
    0.68
    новниш
    0.67
    UnusedPrivate
    0.66
     Reverso
    0.65
    Activations Density 31.237%

    No Known Activations