© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4007
    Prev
    Next
    INDEX
    Explanations

    SQL code snippets and terminology

    oai_token-act-pair · gemini-2.0-flash

    Code/database queries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WireFormatLite
    -0.48
    invokeLater
    -0.45
     Norvège
    -0.44
    bewerken
    -0.41
     Goldsmith
    -0.40
    WithIOException
    -0.40
    ArgumentParser
    -0.40
    bcryptjs
    -0.39
    ajur
    -0.39
    PyObject
    -0.38
    POSITIVE LOGITS
     connect
    0.61
     FetchType
    0.59
     root
    0.59
     Connect
    0.57
     Trich
    0.55
    IGraphics
    0.54
    connect
    0.53
     connection
    0.53
    Autoritní
    0.52
    root
    0.52
    Activations Density 1.166%

    No Known Activations