© 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. 9774
    Prev
    Next
    INDEX
    Explanations

    what appears to be code, names, and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    IF

    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
    abestanden
    -0.74
    tvguidetime
    -0.72
    TargetException
    -0.66
    ViewFeatures
    -0.64
     dignité
    -0.60
    eli
    -0.56
     AssemblyProduct
    -0.54
    itária
    -0.53
    Holes
    -0.52
    ut
    -0.52
    POSITIVE LOGITS
    <bos>
    1.09
    loom
    0.59
    DockStyle
    0.57
     Iain
    0.55
    ải
    0.54
    Iain
    0.52
    queur
    0.52
     wier
    0.52
     daim
    0.50
     Beaumont
    0.49
    Activations Density 1.143%

    No Known Activations