© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9742
    Prev
    Next
    INDEX
    Explanations

    code snippets from different programming languages along with networking terminology

    oai_token-act-pair · gemini-2.0-flash

    code and scripting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    extérieur
    -0.52
     abstrait
    -0.52
     neutre
    -0.50
    ^(@)
    -0.50
    pannt
    -0.50
    estimators
    -0.48
    indépendance
    -0.48
     leçons
    -0.48
     quirúrg
    -0.47
    ︎
    -0.47
    POSITIVE LOGITS
    tep
    0.87
    ub
    0.83
    creen
    0.76
    ave
    0.72
    hape
    0.71
    hadow
    0.71
    heet
    0.71
    hift
    0.70
    hare
    0.70
    hop
    0.69
    Activations Density 13.119%

    No Known Activations