© 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. 8438
    Prev
    Next
    INDEX
    Explanations

    the phrase "work of art," "prior art," and categories related to arts, damage and insurance.

    oai_token-act-pair · gemini-2.0-flash

    terms related to art

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

    art related

    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
    elos
    -0.50
    BeginContext
    -0.49
     hay
    -0.45
    idh
    -0.45
     Tent
    -0.45
     tent
    -0.44
    //
    -0.44
    packageName
    -0.43
     lou
    -0.43
     गा
    -0.43
    POSITIVE LOGITS
     art
    1.46
     works
    1.29
    art
    1.25
     artwork
    1.21
     artworks
    1.19
    Art
    1.13
     arts
    1.10
     Works
    1.09
     WORKS
    1.09
    works
    1.05
    Activations Density 1.056%

    No Known Activations