© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16093
    Prev
    Next
    INDEX
    Explanations

    the word "We" regardless of context

    oai_token-act-pair · gemini-2.0-flash

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     we
    -0.59
     he
    -0.51
     our
    -0.47
    lö
    -0.46
    rin
    -0.45
     Peter
    -0.45
     protected
    -0.45
    slidesToShow
    -0.45
    vänt
    -0.44
    Сер
    -0.43
    POSITIVE LOGITS
     initComponents
    1.00
     lenker
    0.80
     disambiguazione
    0.73
     betweenstory
    0.73
     CreateTagHelper
    0.73
     يتيمه
    0.72
    Rohy
    0.70
    __(/*!
    0.69
    AndEndTag
    0.68
    usermodel
    0.68
    Activations Density 0.368%

    No Known Activations