© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7129
    Prev
    Next
    INDEX
    Explanations

    LaTeX newline commands

    oai_token-act-pair · gemini-2.0-flash

    \\

    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
    ChildIndex
    -0.66
     ModelExpression
    -0.62
    клопе
    -0.61
     gneiss
    -0.60
    FieldBuilder
    -0.60
    ArrowToggle
    -0.59
    IsMutable
    -0.57
     AssemblyProduct
    -0.57
     springfox
    -0.56
     kites
    -0.52
    POSITIVE LOGITS
    出版年
    0.61
    躇
    0.59
    anyon
    0.57
    endforeach
    0.54
    Datuak
    0.50
    outState
    0.50
    calipsis
    0.50
    ypress
    0.49
    PDIR
    0.48
     memer
    0.47
    Activations Density 0.305%

    No Known Activations