© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13004
    Prev
    Next
    INDEX
    Explanations

    the letters "bea", "rie", "sie", or "ile"

    oai_token-act-pair · gemini-2.0-flash

    Code and research

    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
    Rujuakan
    -0.69
    endphp
    -0.68
    Hozzáférés
    -0.66
     виправивши
    -0.65
    ParallelGroup
    -0.62
     estimés
    -0.62
    XmlAccessType
    -0.60
    Portale
    -0.60
    setContentView
    -0.59
     Мексичка
    -0.59
    POSITIVE LOGITS
     major
    0.50
    خطيط
    0.48
    ming
    0.46
    Története
    0.44
    pr
    0.43
    cshtml
    0.43
    hella
    0.43
    vy
    0.43
    mo
    0.42
     görüş
    0.42
    Activations Density 0.557%

    No Known Activations