© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2991
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    qrstuvwxyz
    -0.51
    ције
    -0.46
    GetKeyDown
    -0.42
    ViewImports
    -0.42
     Muse
    -0.42
     rač
    -0.41
     expended
    -0.40
    *********
    -0.40
    FOOTNOTES
    -0.39
    ambiguation
    -0.39
    POSITIVE LOGITS
    VersionUID
    0.79
     kasarigan
    0.77
     <>",
    0.74
    ientí
    0.73
    RegressionTest
    0.73
     createState
    0.71
    istoitu
    0.69
    parsedMessage
    0.66
    MENAFN
    0.65
     للاسماء
    0.65
    Activations Density 4.912%

    No Known Activations