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

    the term "drag" as it relates to racing or resistance, as well as engineering contexts like mining or engine design

    oai_token-act-pair · gemini-2.0-flash

    drag

    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
    Not in Any Lists

    No Comments

    Negative Logits
     drag
    -0.94
     drags
    -0.84
     Drag
    -0.84
    drag
    -0.82
    Drag
    -0.82
     INTERESAR
    -0.77
     DRAG
    -0.76
    存于互联网档案馆
    -0.76
     dragging
    -0.75
     Bias
    -0.72
    POSITIVE LOGITS
    <bos>
    1.20
    '
    0.60
    </i>
    0.60
    ."
    0.60
    "
    0.58
    ‘
    0.55
    webElementXpaths
    0.54
    </b>
    0.54
    “
    0.54
    .”
    0.53
    Activations Density 1.830%

    No Known Activations