© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5493
    Prev
    Next
    INDEX
    Explanations

    content related to blog posts and personal updates, including internet shorthand, greetings, weather, current activities, and reading habits

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Baillargeon
    -0.65
     ),
    -0.61
    DispatchToProps
    -0.54
     defStyleAttr
    -0.54
     ویکی‌پدیای
    -0.53
     suivantes
    -0.52
     [],
    -0.50
    ImageContext
    -0.49
     Roskov
    -0.49
     toalha
    -0.49
    POSITIVE LOGITS
    ?
    0.82
    !
    0.79
    makeText
    0.69
    ।
    0.63
    ГЛА
    0.62
     ***!
    0.62
    cshtml
    0.60
    jsxFileName
    0.60
    ">
    0.59
     ??
    0.56
    Activations Density 7.035%

    No Known Activations