© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15127
    Prev
    Next
    INDEX
    Explanations

    content about athletes turning professional.

    oai_token-act-pair · gemini-2.0-flash

    professional

    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
     protoimpl
    -0.60
    İstinadlar
    -0.54
    Gweler
    -0.52
    windowFixed
    -0.50
    ayakan
    -0.50
    ]--;
    -0.49
    endphp
    -0.49
    UOUS
    -0.48
    numerusform
    -0.48
     العنوان
    -0.48
    POSITIVE LOGITS
     pro
    1.37
     professional
    1.27
    Professional
    1.20
     Professional
    1.17
    professional
    1.12
     PROFESSIONAL
    1.11
     profesional
    1.09
    pro
    1.06
     profissional
    1.01
     professionnelle
    1.01
    Activations Density 1.095%

    No Known Activations