© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11977
    Prev
    Next
    INDEX
    Explanations

    the word "draw" or "drawing" followed by words related to attention, extraction, or influence

    oai_token-act-pair · gemini-2.0-flash

    draw

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AddTagHelper
    -0.56
    存于互联网档案馆
    -0.49
    yntaxException
    -0.49
     Abre
    -0.48
    МА
    -0.45
    serif
    -0.43
    elope
    -0.43
    BeginInit
    -0.43
     Drawn
    -0.43
    UB
    -0.42
    POSITIVE LOGITS
    setFrom
    0.58
     بيها
    0.58
    transQ
    0.57
    ьаж
    0.55
     приходится
    0.55
    NullException
    0.52
     sguardo
    0.52
     fallu
    0.52
     giudi
    0.51
     illet
    0.51
    Activations Density 3.135%

    No Known Activations