© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13869
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    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
     StatelessWidget
    -0.82
     utafitiHapana
    -0.79
    ViewFeatures
    -0.63
    
    -0.63
    BagLayout
    -0.62
    BeginContext
    -0.61
     stiefel
    -0.60
    ItemLayout
    -0.60
    Tikang
    -0.59
     StatefulWidget
    -0.59
    POSITIVE LOGITS
     propOrder
    0.54
    apimachinery
    0.46
     versioni
    0.46
    mlung
    0.45
     ویکی‌پدیای
    0.44
     hiyo
    0.44
    cracker
    0.43
    FTFY
    0.42
     FormGroup
    0.42
    ”]
    0.41
    Activations Density 2.013%

    No Known Activations