© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2559
    Prev
    Next
    INDEX
    Explanations

    code package names, especially those including "psaravan"

    oai_token-act-pair · gemini-2.0-flash

    importing packages/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RectangleBorder
    -0.69
    StoryboardSegue
    -0.68
     poffe
    -0.63
     myſelf
    -0.63
     ExecuteAsync
    -0.63
     juſt
    -0.62
    PMailer
    -0.61
     reaſon
    -0.60
    ">//
    -0.60
     himſelf
    -0.59
    POSITIVE LOGITS
     atuação
    0.48
     nisi
    0.48
     je
    0.46
     Southern
    0.45
    versi
    0.44
    WithIdentifier
    0.44
    logna
    0.44
    werb
    0.43
    AccessorTable
    0.42
     dois
    0.41
    Activations Density 10.991%

    No Known Activations