© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10920
    Prev
    Next
    INDEX
    Explanations

    mostly LaTeX math markup interspersed with occasional snippets of other languages

    oai_token-act-pair · gemini-2.0-flash

    mathematical formulas or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ScopeManager
    -0.74
     MainAxisSize
    -0.73
    witched
    -0.56
     Akismet
    -0.56
     RISERV
    -0.56
     Foul
    -0.55
    Portale
    -0.54
     visuales
    -0.54
    OutputType
    -0.54
     Kitts
    -0.53
    POSITIVE LOGITS
    <bos>
    2.09
    ’
    0.68
     transfieras
    0.65
    '
    0.63
     />\
    0.57
     ddelweddau
    0.54
    webElementXpaths
    0.53
    олові
    0.52
     }</
    0.51
    \
    0.48
    Activations Density 0.507%

    No Known Activations