© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15624
    Prev
    Next
    INDEX
    Explanations

    words occurring in code, especially related to UI, game engines, and compilers

    oai_token-act-pair · gemini-2.0-flash

    Code/Programming

    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
     I
    -0.48
     Ur
    -0.42
     for
    -0.41
    endl
    -0.40
    </h5>
    -0.39
    <eos>
    -0.39
     B
    -0.39
     E
    -0.39
     wirst
    -0.39
    </h1>
    -0.38
    POSITIVE LOGITS
     Reſ
    1.02
     betweenstory
    0.95
     Majefty
    0.94
     OFDb
    0.94
     esternos
    0.92
    IntoConstraints
    0.90
    ſelf
    0.89
    URLException
    0.88
     Houſe
    0.86
     Monfieur
    0.86
    Activations Density 2.668%

    No Known Activations