© 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. 15638
    Prev
    Next
    INDEX
    Explanations

    statements of causality or credit

    oai_token-act-pair · gemini-2.0-flash

    assigning/attributing

    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
     gekozen
    -0.60
    XmlEnum
    -0.58
     TType
    -0.57
    UrlResolution
    -0.56
     AssemblyTitle
    -0.54
     bedoeld
    -0.54
     rédig
    -0.52
     écl
    -0.52
     cappuccio
    -0.52
     stunned
    -0.52
    POSITIVE LOGITS
     assigning
    0.78
     attribute
    0.78
     assign
    0.76
     assigns
    0.76
     pin
    0.76
     att
    0.75
     pinning
    0.75
     finger
    0.72
     attribut
    0.68
     assignment
    0.68
    Activations Density 1.566%

    No Known Activations