© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 926
    Prev
    Next
    INDEX
    Explanations

    text from academic papers describing the mathematical methods used in the paper

    oai_token-act-pair · gemini-2.0-flash

    proposing

    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
     Theſe
    -0.80
     itſelf
    -0.75
     Anſ
    -0.73
     Shakspeare
    -0.71
    onActivityResult
    -0.71
     myſelf
    -0.71
     Reſ
    -0.68
     JAS
    -0.63
     rainbows
    -0.62
     ―――――
    -0.62
    POSITIVE LOGITS
     multi
    0.59
    FailureListener
    0.51
    :✨
    0.50
     EconPapers
    0.50
    AnchorTagHelper
    0.50
     auto
    0.49
     U
    0.49
     multiple
    0.47
    SuspendLayout
    0.47
    idjan
    0.47
    Activations Density 6.469%

    No Known Activations