© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15561
    Prev
    Next
    INDEX
    Explanations

    angle brackets such as in HTML or XML, and also certain programming terms.

    oai_token-act-pair · gemini-2.0-flash

    code, websites

    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
    Negative Logits
    stonia
    -0.52
    ByExample
    -0.50
     imp
    -0.49
    jLabel
    -0.48
    styleType
    -0.47
    DropTable
    -0.47
    VertexAttrib
    -0.46
    nonce
    -0.46
     الرياضيه
    -0.45
    به
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.65
     disambiguazione
    0.65
     Riproduzione
    0.62
    reportWebVitals
    0.57
    gjenge
    0.56
    Rhestr
    0.54
     kasarigan
    0.53
    Còn
    0.52
    onOptions
    0.52
    ंदीखरीदारी
    0.52
    Activations Density 1.491%

    No Known Activations