© 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. 7889
    Prev
    Next
    INDEX
    Explanations

    the word "choice" or its variations, which often appears in the context of making decisions or expressing preference

    oai_token-act-pair · gemini-2.0-flash

    choice

    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
     choice
    -2.94
    choice
    -2.63
     Choice
    -2.59
    Choice
    -2.58
     choices
    -2.31
     CHOICE
    -2.31
     choix
    -2.02
    CHOICE
    -1.99
     Choices
    -1.98
    Choices
    -1.89
    POSITIVE LOGITS
     Roskov
    0.79
    WillAppear
    0.66
     noqa
    0.63
     CascadeType
    0.60
     fieldNum
    0.59
    __*/
    0.59
    geries
    0.59
    ielo
    0.58
    artige
    0.58
     JAXBElement
    0.56
    Activations Density 0.201%

    No Known Activations