© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7583
    Prev
    Next
    INDEX
    Explanations

    mentions of sports, especially racing championships

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "field"

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

    field

    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
    RenderAtEndOf
    -0.64
     sih
    -0.48
    ècie
    -0.48
    SDAY
    -0.47
     chó
    -0.46
    Rhône
    -0.45
     marmo
    -0.45
     onAnimation
    -0.45
    BRARY
    -0.45
    hlor
    -0.45
    POSITIVE LOGITS
     field
    2.20
    field
    1.73
     Field
    1.69
     fields
    1.68
     FIELD
    1.65
    Field
    1.59
    FIELD
    1.44
    fields
    1.34
     Fields
    1.31
     FIELDS
    1.24
    Activations Density 0.738%

    No Known Activations