© 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. 5263
    Prev
    Next
    INDEX
    Explanations

    terminology related to reclining chairs and their mechanisms

    oai_token-act-pair · gemini-2.0-flash

    recliners

    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
    getDoctrine
    -0.56
     незавершена
    -0.55
     שוליים
    -0.52
    Geplaatst
    -0.51
    resizingMask
    -0.50
    Prophet
    -0.49
     LEYENDO
    -0.47
     FontWeight
    -0.47
     Prophet
    -0.46
    domain
    -0.44
    POSITIVE LOGITS
     AssemblyTitle
    0.71
    WireFormatLite
    0.66
    FormTagHelper
    0.61
    AccessorTable
    0.56
    #
    0.54
     fieldNum
    0.52
    ogen
    0.52
    }{*}{}
    0.51
     rolling
    0.51
     fronts
    0.50
    Activations Density 1.748%

    No Known Activations