© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6543
    Prev
    Next
    INDEX
    Explanations

    keywords and names of functions, methods, and variables across a variety of programming languages.

    oai_token-act-pair · gemini-2.0-flash

    code syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     "
    -0.60
     “
    -0.54
     surla
    -0.49
    :
    -0.48
     
    -0.47
    :@"
    -0.46
    ","
    -0.44
     See
    -0.44
    ].
    -0.43
    :.
    -0.43
    POSITIVE LOGITS
    (_
    0.85
    (
    0.84
    MLLoader
    0.84
    ViewFeatures
    0.80
    (){}
    0.79
    ()
    0.79
    ValueStyle
    0.75
     houſe
    0.74
    (...
    0.74
     juridiques
    0.73
    Activations Density 0.715%

    No Known Activations