© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9796
    Prev
    Next
    INDEX
    Explanations

    words relating to responsibilities, guidance and help, especially in law, medicine, and finance

    oai_token-act-pair · gemini-2.0-flash

    roles in healthcare and research

    np_token-act-pair-logits · gpt-4o-mini

    Helping people/businesses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Bäume
    -0.49
    Спасылкі
    -0.45
     internetowa
    -0.41
    そちら
    -0.36
    <bos>
    -0.35
    Pro
    -0.35
    イルド
    -0.35
     chimiques
    -0.34
    stellen
    -0.34
    СР
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.87
     practitioners
    0.85
     operators
    0.84
     creators
    0.79
     designers
    0.79
     researchers
    0.76
     clinicians
    0.75
    脚注の使い方
    0.75
     للمعارف
    0.75
     lenders
    0.74
    Activations Density 4.360%

    No Known Activations