© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6090
    Prev
    Next
    INDEX
    Explanations

    mentions of painting, drawing, and art in general.

    oai_token-act-pair · gemini-2.0-flash

    paint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     paint
    -2.73
    paint
    -2.39
     painting
    -2.34
     Paint
    -2.34
     PAINT
    -2.27
    Paint
    -2.23
     painted
    -2.17
     paints
    -2.14
     Painting
    -2.09
    painting
    -2.09
    POSITIVE LOGITS
    χρι
    0.59
     فريبيس
    0.55
    endphp
    0.55
     Favre
    0.55
    chyma
    0.53
     verzichten
    0.53
    بير
    0.50
     Anthology
    0.50
     gentry
    0.50
    __':
    0.49
    Activations Density 1.879%

    No Known Activations