© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15309
    Prev
    Next
    INDEX
    Explanations

    snippets of code or formal documents, specifically looking for a mix of uppercase letters, punctuation, and potentially math symbols

    oai_token-act-pair · gemini-2.0-flash

    French

    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
    Negative Logits
     cables
    -1.17
     wrappers
    -1.16
     envelopes
    -1.14
     seats
    -1.13
     checkpoints
    -1.13
     batteries
    -1.13
     bottles
    -1.13
     समीक्षाओं
    -1.12
     monuments
    -1.12
     boxes
    -1.11
    POSITIVE LOGITS
     prochaines
    0.36
     lèvres
    0.33
     vérit
    0.29
     épaules
    0.26
     côtés
    0.25
    ската
    0.25
     oreilles
    0.24
     églises
    0.24
     autorités
    0.24
    ルー
    0.23
    Activations Density 2.062%

    No Known Activations