© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7846
    Prev
    Next
    INDEX
    Explanations

    things that look like HTML

    oai_token-act-pair · gemini-2.0-flash

    tax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    nasel
    -0.52
    ](#
    -0.48
     متحده
    -0.48
     surla
    -0.48
    stellungs
    -0.48
    новништво
    -0.47
     ناش
    -0.47
     xuyên
    -0.47
     String
    -0.47
     pad
    -0.45
    POSITIVE LOGITS
     tax
    0.98
    Tax
    0.79
     Tax
    0.79
    tax
    0.77
    TAX
    0.76
     TAX
    0.75
     referenties
    0.68
    Datuak
    0.63
    税
    0.61
    ArrowToggle
    0.60
    Activations Density 1.651%

    No Known Activations