© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3051
    Prev
    Next
    INDEX
    Explanations

    text from privacy policies on a website

    oai_token-act-pair · gemini-2.0-flash

    data privacy

    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
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.65
    ANTIC
    -0.58
     FishBase
    -0.54
    antMatchers
    -0.51
     Cardoso
    -0.51
    werkers
    -0.48
    gian
    -0.48
     StringTokenizer
    -0.47
    ensation
    -0.47
    Izvori
    -0.47
    POSITIVE LOGITS
     resourceCulture
    0.76
    webElementXpaths
    0.53
    جغرافيا
    0.52
     henvisninger
    0.51
     AssemblyCulture
    0.50
    richTextPanel
    0.48
    MLLoader
    0.47
    SourceChecksum
    0.47
     himo
    0.47
    ulink
    0.46
    Activations Density 2.450%

    No Known Activations