© 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. 10903
    Prev
    Next
    INDEX
    Explanations

    blocks of code with keywords like "Promise", "err", "error", "form", "new", or "function"

    oai_token-act-pair · gemini-2.0-flash

    open parenthesis

    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
    <bos>
    -0.75
    (
    -0.50
     promozione
    -0.44
     fourrure
    -0.44
    پیوند
    -0.43
     mukana
    -0.42
     squadre
    -0.40
     tapaht
    -0.40
     følge
    -0.39
     toiminta
    -0.39
    POSITIVE LOGITS
    aarrggbb
    0.90
     InputDecoration
    0.90
    存于互联网档案馆
    0.89
    StoryboardSegue
    0.83
     kasarigan
    0.83
     ivelany
    0.79
    AsUp
    0.77
    DispatchToProps
    0.77
    igshid
    0.75
    ########.
    0.73
    Activations Density 11.498%

    No Known Activations