© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 14051
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "painting" or words related to it.

    oai_token-act-pair · gemini-2.0-flash

    painting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     painting
    -1.02
     paintings
    -1.01
     Painting
    -0.81
    painting
    -0.78
     sculpture
    -0.78
     Paintings
    -0.77
     artwork
    -0.71
     artworks
    -0.66
     sculptures
    -0.62
     statue
    -0.61
    POSITIVE LOGITS
    fjspx
    0.93
    دانشنامهٔ
    0.85
    InjectAttribute
    0.80
    ViewFeatures
    0.77
    клопе
    0.66
    Personensuche
    0.66
    UserScript
    0.65
    NameInMap
    0.65
    jgl
    0.61
     externi
    0.61
    Activations Density 1.297%

    No Known Activations