© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10767
    Prev
    Next
    INDEX
    Explanations

    Android code related to setting the text property of UI elements

    oai_token-act-pair · gemini-2.0-flash

    txt

    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
    setText
    -0.86
     تضيفلها
    -0.70
     text
    -0.68
    texts
    -0.67
     Text
    -0.66
     tex
    -0.65
    TEXT
    -0.65
    text
    -0.64
    getText
    -0.64
    ngoing
    -0.63
    POSITIVE LOGITS
    <bos>
    1.52
    ForValue
    0.54
     مرئيه
    0.54
    ędzynarod
    0.52
     oiseaux
    0.52
     Efq
    0.52
    '
    0.50
     acrylique
    0.50
     Monfieur
    0.50
     résist
    0.49
    Activations Density 0.171%

    No Known Activations