© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11329
    Prev
    Next
    INDEX
    Explanations

    code snippets containing keywords related to file paths, URLs, and resolving dependencies.

    oai_token-act-pair · gemini-2.0-flash

    raw equal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Datuak
    -0.59
     createSprite
    -0.58
    AndEndTag
    -0.58
    ruptedException
    -0.57
     '{@
    -0.53
    RectangleBorder
    -0.53
    makeText
    -0.52
    ngdoc
    -0.52
    JspWriter
    -0.52
    yargs
    -0.51
    POSITIVE LOGITS
     normaux
    0.69
     marquées
    0.62
    webElementXpaths
    0.60
     وتسجيلات
    0.59
     EconPapers
    0.59
    بالإ
    0.58
     investissements
    0.58
    )]
    0.57
    ?")
    0.57
     *
    0.56
    Activations Density 1.518%

    No Known Activations