© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5142
    Prev
    Next
    INDEX
    Explanations

    text associated with research findings

    oai_token-act-pair · gemini-2.0-flash

    results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     results
    -2.58
    results
    -2.30
     Results
    -2.22
    Results
    -2.09
     RESULTS
    -1.94
     resultados
    -1.76
    RESULTS
    -1.73
     résultats
    -1.72
     resultaten
    -1.62
     Ergebnisse
    -1.59
    POSITIVE LOGITS
    UpInside
    0.73
    ksikon
    0.54
     salve
    0.52
    المناصب
    0.52
     препратки
    0.48
    tagens
    0.48
    mstyle
    0.48
    spaceBetween
    0.47
    ategorien
    0.47
    :✨
    0.46
    Activations Density 0.814%

    No Known Activations