© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3983
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to math, probabilities, and code

    oai_token-act-pair · gemini-2.0-flash

    code/math/technical

    np_max-act · 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
    parsedMessage
    -0.57
     of
    -0.46
     end
    -0.46
     fer
    -0.42
    endo
    -0.42
     {
    -0.41
     =
    -0.41
    èdia
    -0.41
    veyard
    -0.41
    ellas
    -0.40
    POSITIVE LOGITS
     Roskov
    0.82
    invokeLater
    0.78
    +#+#
    0.73
     pinulongan
    0.71
    WithIOException
    0.68
    Suara
    0.66
    AccessorTable
    0.66
     postIndex
    0.66
     Obrador
    0.63
    BeginInit
    0.62
    Activations Density 7.457%

    No Known Activations