© 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. 11976
    Prev
    Next
    INDEX
    Explanations

    words related to Lithuanian places and organizations during World War II

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or coding terms

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

    Lithuanian places

    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
     lendemain
    -0.48
    WebServlet
    -0.45
    viene
    -0.40
    reportWebVitals
    -0.39
    quelize
    -0.38
    tamen
    -0.36
     зато
    -0.35
    erville
    -0.35
    聞
    -0.34
     competitiveness
    -0.34
    POSITIVE LOGITS
    MLLoader
    0.96
     AssemblyCulture
    0.73
    onomía
    0.68
    AnchorStyles
    0.67
     MenuView
    0.67
    aarrggbb
    0.65
    حوالہ
    0.65
    brido
    0.65
     AppCompatTheme
    0.64
     متعلقه
    0.64
    Activations Density 0.087%

    No Known Activations