© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12077
    Prev
    Next
    INDEX
    Explanations

    the word "node" in what seems to be a description of a computer network

    oai_token-act-pair · gemini-2.0-flash

    node

    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
     typelib
    -1.05
    RegressionTest
    -1.03
    migrationBuilder
    -1.02
    ьаж
    -0.94
    complexContent
    -0.93
    RTLD
    -0.89
     sahaja
    -0.88
    FunctionFlags
    -0.86
    webElementXpaths
    -0.85
     كومونز
    -0.84
    POSITIVE LOGITS
     periodicity
    0.84
     Babylonian
    0.83
     Cæsar
    0.76
    o
    0.75
     vocale
    0.75
     Shakspeare
    0.75
     stabilization
    0.74
     Agamemnon
    0.72
     privatization
    0.71
    (
    0.71
    Activations Density 1.475%

    No Known Activations