© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 406
    Prev
    Next
    INDEX
    Explanations

    HTML tags like div, form, and ul, as well as Javascript selectors (e.g. $), and the word 'you'

    oai_token-act-pair · gemini-2.0-flash

    code and website content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    SourceChecksum
    -0.83
    NameInMap
    -0.82
    AndEndTag
    -0.70
     EconPapers
    -0.69
     noDo
    -0.69
    ंदीखरीदारी
    -0.69
     Roskov
    -0.67
     виправивши
    -0.65
    IntoConstraints
    -0.65
    abestanden
    -0.64
    POSITIVE LOGITS
    manship
    0.52
     /\.
    0.48
    </code>
    0.43
    inquirer
    0.43
    wps
    0.42
     visiting
    0.42
     buiten
    0.41
    Général
    0.40
    </blockquote>
    0.39
    GeneratedCode
    0.39
    Activations Density 6.536%

    No Known Activations