© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11542
    Prev
    Next
    INDEX
    Explanations

    Swift Protobuf code, especially keywords and code structures

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     double
    -2.25
    double
    -1.93
     single
    -1.80
     Double
    -1.75
    Double
    -1.71
     DOUBLE
    -1.69
    single
    -1.64
     doble
    -1.60
     Single
    -1.59
    Single
    -1.50
    POSITIVE LOGITS
    Tembelea
    0.74
     Wikimedijinoj
    0.71
     ComVisible
    0.70
    AndEndTag
    0.66
     createState
    0.64
     linkovi
    0.59
     resourceCulture
    0.58
    ViewImports
    0.57
     HttpNotFound
    0.55
    UnusedPrivate
    0.55
    Activations Density 2.031%

    No Known Activations