© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14395
    Prev
    Next
    INDEX
    Explanations

    code import statements pointing to github.com

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    reszcie
    -0.55
     gärna
    -0.54
     themſelves
    -0.52
     daß
    -0.51
     myſelf
    -0.49
     becauſe
    -0.49
    клопе
    -0.48
    berdayakan
    -0.47
     itſelf
    -0.47
     occorre
    -0.47
    POSITIVE LOGITS
    adaptiveStyles
    0.68
    cshtml
    0.64
    SizeMode
    0.63
    GroupLayout
    0.60
     AssemblyProduct
    0.58
    WebElementEntity
    0.58
    FilterChain
    0.57
    HandlerContext
    0.56
     resourceCulture
    0.55
    /*---
    0.54
    Activations Density 0.150%

    No Known Activations