© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 797
    Prev
    Next
    INDEX
    Explanations

    web URLs and related terms like "docs", "com", "http", "aws", and "site"

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
    Not in Any Lists

    No Comments

    Negative Logits
     interpr
    -0.46
     économique
    -0.43
     ama
    -0.43
     Ropa
    -0.41
     bal
    -0.41
     tab
    -0.41
     Reuse
    -0.41
     bala
    -0.40
    AutoresizingMask
    -0.40
    เก
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.86
     AssemblyTitle
    0.85
     Administrativna
    0.83
    styleType
    0.80
     himo
    0.79
     ſeveral
    0.78
    webElementXpaths
    0.75
    Obrázky
    0.71
    Portale
    0.69
    IndentedString
    0.69
    Activations Density 2.834%

    No Known Activations