© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11633
    Prev
    Next
    INDEX
    Explanations

    words related to professional medical and legal settings

    oai_token-act-pair · gemini-2.0-flash

    recognizing "context"

    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
    OGND
    -0.77
     متعلقه
    -0.73
     WebDriverWait
    -0.73
     pleaſure
    -0.68
    ViewFeatures
    -0.66
    fromnode
    -0.65
     <",
    -0.65
    WithIdentifier
    -0.61
    SourceChecksum
    -0.60
     للاسماء
    -0.57
    POSITIVE LOGITS
     context
    2.20
    context
    1.82
     contexts
    1.73
     Context
    1.65
     contexto
    1.60
    Context
    1.56
     contexte
    1.50
     setting
    1.48
     CONTEXT
    1.44
    contexts
    1.39
    Activations Density 2.940%

    No Known Activations