© 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. 1083
    Prev
    Next
    INDEX
    Explanations

    references to blogs and blog posts, and sometimes references to people and companies

    oai_token-act-pair · gemini-2.0-flash

    blog

    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
     للاسماء
    -0.79
     سكانية
    -0.74
     >=",
    -0.73
    HtmlAttribute
    -0.68
    contentLoaded
    -0.68
    saraba
    -0.63
     EnglishChoose
    -0.61
    UnsafeEnabled
    -0.60
     himo
    -0.59
     kasarigan
    -0.57
    POSITIVE LOGITS
     blog
    2.06
     blogs
    1.80
     Blog
    1.74
    blog
    1.71
    Blog
    1.65
     BLOG
    1.60
     blogging
    1.54
    BLOG
    1.52
     Blogs
    1.52
    blogs
    1.48
    Activations Density 1.414%

    No Known Activations