© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9479
    Prev
    Next
    INDEX
    Explanations

    film credits, design credits, and the word 'by' introducing people's names.

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or concepts

    np_token-act-pair-logits · gpt-4o-mini

    credits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     box
    -0.47
     corporal
    -0.47
    ędzynarod
    -0.44
     setw
    -0.44
     body
    -0.43
    atron
    -0.43
     XIII
    -0.42
    setConfig
    -0.41
     REST
    -0.41
    box
    -0.41
    POSITIVE LOGITS
    aarrggbb
    0.80
     propOrder
    0.74
     bezeichneter
    0.68
    MethodManager
    0.66
     XCTest
    0.61
    OGND
    0.60
     ostavi
    0.60
    CrossRef
    0.59
     Wicidata
    0.59
    mybatisplus
    0.58
    Activations Density 0.342%

    No Known Activations