© 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. 10886
    Prev
    Next
    INDEX
    Explanations

    the prefix "bro" in words, possibly related to "brotherhood" or slang

    oai_token-act-pair · gemini-2.0-flash

    the term "bro" in various capitalizations

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

    bro

    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
     CommonModule
    -0.56
    argout
    -0.46
    hiana
    -0.46
    pch
    -0.45
     digital
    -0.44
    ApplicationTests
    -0.43
    SpringBoot
    -0.42
    atos
    -0.42
     nos
    -0.41
     conto
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.72
    SharedCtor
    0.72
    astéroïdes
    0.66
     propOrder
    0.65
     pageContext
    0.63
    AndEndTag
    0.61
     otomatig
    0.60
     لينك
    0.59
    Datuak
    0.59
    Hentet
    0.59
    Activations Density 0.252%

    No Known Activations