© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1718
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to context, environment, settings, and situations

    oai_token-act-pair · gemini-2.0-flash

    context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     context
    -0.85
     contextes
    -0.85
     environment
    -0.84
     Environment
    -0.83
     contexte
    -0.82
     Context
    -0.79
    CONTEXT
    -0.76
     environments
    -0.75
     CONTEXT
    -0.75
     contexts
    -0.74
    POSITIVE LOGITS
    MessageOf
    0.59
     otomatig
    0.57
    RenderAtEndOf
    0.54
     pass
    0.52
    Tikang
    0.49
     ***!
    0.49
     AssemblyCulture
    0.49
    WebServlet
    0.48
     invokingState
    0.47
     passes
    0.46
    Activations Density 37.915%

    No Known Activations