© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11767
    Prev
    Next
    INDEX
    Explanations

    passages related to art and drawing

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

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

    drawing

    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
     painting
    -1.32
     painted
    -1.25
     paint
    -1.21
     Painting
    -1.20
    painting
    -1.13
     painters
    -1.13
     painter
    -1.13
     PAINT
    -1.09
     paints
    -1.09
    paint
    -1.09
    POSITIVE LOGITS
    MockBean
    0.75
    ImageContext
    0.74
    zaamheid
    0.50
     елның
    0.49
     couvercle
    0.48
    abetes
    0.47
    NavController
    0.47
    RenderAtEndOf
    0.47
    éroport
    0.47
    ArgsConstructor
    0.47
    Activations Density 1.107%

    No Known Activations