© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11809
    Prev
    Next
    INDEX
    Explanations

    code delimiters such as curly brackets, parentheses and semicolons

    oai_token-act-pair · gemini-2.0-flash

    Code and API related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ummer
    -0.54
    ↵↵
    -0.49
     Fleck
    -0.48
    irez
    -0.48
    Tracer
    -0.45
     yana
    -0.45
    ]')
    -0.44
     nghi
    -0.44
     siker
    -0.44
     hiperten
    -0.43
    POSITIVE LOGITS
    __((
    0.75
    Tikang
    0.74
    Personensuche
    0.71
    :+:
    0.69
     EconPapers
    0.66
     mergeFrom
    0.63
    CodeAnalysis
    0.62
    AnchorStyles
    0.62
     кӀ
    0.61
    (!__
    0.61
    Activations Density 0.568%

    No Known Activations