© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9986
    Prev
    Next
    INDEX
    Explanations

    section headings or breaks in the text

    oai_token-act-pair · gemini-2.0-flash

    Scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Personensuche
    -0.88
    <bos>
    -0.88
     AssemblyCulture
    -0.82
    webElementXpaths
    -0.81
     تضيفلها
    -0.74
     <=",
    -0.68
     Taktlose
    -0.66
     ویکی‌پدی
    -0.66
     disambiguazione
    -0.66
    MigrationBuilder
    -0.65
    POSITIVE LOGITS
    êmio
    0.36
    omentos
    0.36
     Theſe
    0.36
    fazione
    0.35
     Derfor
    0.35
     @{
    0.35
     gabinete
    0.34
     siv
    0.33
     Shakspeare
    0.33
     houſe
    0.33
    Activations Density 1.603%

    No Known Activations