© 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. 12670
    Prev
    Next
    INDEX
    Explanations

    C/C++ code syntax, especially struct definitions, function definitions and dereferencing

    oai_token-act-pair · gemini-2.0-flash

    struct

    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
     houſe
    -0.75
     Jefus
    -0.69
     becauſe
    -0.66
     ſeveral
    -0.66
     ſtate
    -0.65
     Houſe
    -0.65
     againſt
    -0.64
    writeField
    -0.63
     neceff
    -0.62
     preſent
    -0.62
    POSITIVE LOGITS
    mkdirs
    0.59
    iotti
    0.59
     led
    0.56
     disponibilités
    0.56
    Files
    0.54
     thu
    0.54
     den
    0.54
     file
    0.53
    IKAN
    0.53
    FLOW
    0.52
    Activations Density 1.410%

    No Known Activations