© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4827
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific and medical research

    oai_token-act-pair · gemini-2.0-flash

    words with 'self' prefix

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

    results

    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
     
    -0.82
    <unused61>
    -0.81
    <unused62>
    -0.79
    <unused63>
    -0.77
    1
    -0.75
    2
    -0.73
    <unused60>
    -0.72
    3
    -0.70
    <strong>
    -0.69
    <eos>
    -0.68
    POSITIVE LOGITS
     Theſe
    1.48
     itſelf
    1.39
     myſelf
    1.26
     bezeichneter
    1.23
     ویکی‌آمباردا
    1.22
    ſelf
    1.20
     Monfieur
    1.18
     متعلقه
    1.15
     betweenstory
    1.13
    parsedMessage
    1.13
    Activations Density 15.409%

    No Known Activations