© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    phrases about dependence or relation of one action on another.

    oai_token-act-pair · gemini-2.0-flash

    reaction

    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
     loosing
    -0.74
     שוליים
    -0.72
     nakalista
    -0.71
     fhew
    -0.70
    ibatkan
    -0.70
    ingeki
    -0.69
    wahati
    -0.69
    WebServlet
    -0.69
     vectorielle
    -0.68
    好好的
    -0.68
    POSITIVE LOGITS
     nominally
    0.67
    <eos>
    0.52
    sibly
    0.52
     broadly
    0.50
    الدراسه
    0.50
    umab
    0.50
    besondere
    0.48
     ostensibly
    0.47
     early
    0.45
    pytest
    0.45
    Activations Density 1.611%

    No Known Activations