© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14235
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to find snippets of code and Arabic script

    oai_token-act-pair · gemini-2.0-flash

    ال

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Leaks
    -0.37
     wheels
    -0.35
     forty
    -0.35
     sixty
    -0.35
     little
    -0.35
    ste
    -0.34
     ninety
    -0.34
     wheel
    -0.34
     fifty
    -0.33
     hundred
    -0.32
    POSITIVE LOGITS
    tagHelperRunner
    0.83
    ViewFeatures
    0.80
    RenderAtEndOf
    0.78
    StoryboardSegue
    0.73
     समीक्षाओं
    0.71
     générations
    0.71
    исленность
    0.69
    setVerticalGroup
    0.68
    ltä
    0.68
     Grecs
    0.67
    Activations Density 0.056%

    No Known Activations