© 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. 9791
    Prev
    Next
    INDEX
    Explanations

    code excerpts or programming-related terms

    oai_token-act-pair · 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
    Gemeinden
    -0.53
    Geplaatst
    -0.52
    ьа
    -0.49
    SBATCH
    -0.47
     AssemblyCulture
    -0.46
    Handlung
    -0.46
     }{@
    -0.46
     pulumi
    -0.45
    Maße
    -0.45
    بوابة
    -0.43
    POSITIVE LOGITS
    OrWhiteSpace
    0.61
     occidentale
    0.56
    AndEndTag
    0.52
     ouvriers
    0.52
    otten
    0.52
     occident
    0.52
     gosto
    0.52
     kişinin
    0.51
    /*---
    0.51
     FontWeight
    0.51
    Activations Density 4.546%

    No Known Activations