© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7963
    Prev
    Next
    INDEX
    Explanations

    the word "choose" and its variants

    oai_token-act-pair · gemini-2.0-flash

    choose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     choose
    -2.20
     choosing
    -1.97
     chooses
    -1.92
    choose
    -1.91
     Choose
    -1.88
     chose
    -1.88
    Choose
    -1.87
    choosing
    -1.73
     Choosing
    -1.72
    Choosing
    -1.70
    POSITIVE LOGITS
    +:+
    0.63
    ReusableCell
    0.54
    ontan
    0.52
    ozat
    0.50
    로드
    0.49
    MessageTagHelper
    0.49
    ứ
    0.48
    rigkeit
    0.48
    ודם
    0.48
    ViewFeatures
    0.47
    Activations Density 0.486%

    No Known Activations