© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9422
    Prev
    Next
    INDEX
    Explanations

    C++ code and CMake commands

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    PerformLayout
    -0.69
     pleaſure
    -0.68
     purpoſe
    -0.68
     greateſt
    -0.64
    IsPostBack
    -0.62
     faſt
    -0.62
     ſame
    -0.61
    ſelf
    -0.60
    zii
    -0.60
     ſtre
    -0.60
    POSITIVE LOGITS
    <bos>
    0.94
    цездатний
    0.62
    IntoConstraints
    0.57
     pinulongan
    0.55
    TintMode
    0.53
     AssemblyTitle
    0.53
     isInitialized
    0.51
     D
    0.49
    oredCriteria
    0.49
    contentLoaded
    0.48
    Activations Density 5.100%

    No Known Activations