© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11573
    Prev
    Next
    INDEX
    Explanations

    words appearing in code snippets or low-level computer architecture discussions

    oai_token-act-pair · gemini-2.0-flash

    writing related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    허
    -0.55
    urlpatterns
    -0.54
    WindowConstants
    -0.53
    IContainer
    -0.51
    gel
    -0.47
    ես
    -0.46
    fer
    -0.46
    зулта
    -0.46
    hahn
    -0.45
     Domin
    -0.44
    POSITIVE LOGITS
     writing
    1.78
     write
    1.71
    writing
    1.69
     Writing
    1.61
    Writing
    1.56
     Write
    1.56
     WRITING
    1.52
    Write
    1.51
    WRITING
    1.50
     writes
    1.48
    Activations Density 2.831%

    No Known Activations