© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11623
    Prev
    Next
    INDEX
    Explanations

    the word "draw" along with words describing planning activities or words describing magic or super-powers

    oai_token-act-pair · gemini-2.0-flash

    draw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     draw
    -2.75
     drawn
    -2.52
     drawing
    -2.50
     draws
    -2.50
     drew
    -2.41
     Draw
    -2.39
    draw
    -2.33
    Draw
    -2.30
     Drawing
    -2.20
    draws
    -2.19
    POSITIVE LOGITS
    PathVariable
    0.50
    cepto
    0.48
    STALK
    0.48
    ãng
    0.48
    Medal
    0.48
    igerung
    0.46
     Bergmann
    0.45
     Tait
    0.45
    ophones
    0.45
    msr
    0.44
    Activations Density 8.326%

    No Known Activations