© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15729
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly javascript or JSON, containing keywords like "function", "promise", "object", "export", "require", or "resolve."

    oai_token-act-pair · gemini-2.0-flash

    Say "("

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    RegressionTest
    -0.59
    til
    -0.46
    lasser
    -0.43
     document
    -0.42
     JTextArea
    -0.40
    hyp
    -0.39
     til
    -0.39
     reminder
    -0.39
     متعلقه
    -0.39
     come
    -0.38
    POSITIVE LOGITS
     mxArray
    0.67
    Cyfeiriadau
    0.67
     MenuView
    0.64
     BoxDecoration
    0.63
     initWithFrame
    0.63
    jetbrains
    0.62
    ForRow
    0.60
     Италијани
    0.60
     defaultstate
    0.59
    %)$
    0.59
    Activations Density 2.252%

    No Known Activations