© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    the letter "R" at the start of a token, especially when followed by other capital letters

    oai_token-act-pair · gemini-2.0-flash

    R

    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
     AssemblyProduct
    -0.50
     "..\..\
    -0.47
     "..\..\..\
    -0.47
    vern
    -0.47
    /.../
    -0.47
    干
    -0.47
    arakhand
    -0.46
    xtext
    -0.45
    setupUi
    -0.45
    lexikon
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.69
     <>",
    0.65
     CreateTagHelper
    0.63
     ostavi
    0.54
     EconPapers
    0.54
     StatefulWidget
    0.53
    :✨
    0.53
    urals
    0.52
    PerformLayout
    0.51
    trino
    0.50
    Activations Density 0.227%

    No Known Activations