Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10969
    Prev
    Next
    INDEX
    Explanations

    words associated with sports, especially soccer

    oai_token-act-pair · gemini-2.0-flash

    words or phrases related to youth

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

    foreign words

    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
    tsin
    -0.52
    \}\\
    -0.45
     ProductService
    -0.43
    fti
    -0.43
     nationally
    -0.41
     Că
    -0.41
     discí
    -0.41
     CHAPITRE
    -0.40
     Besøkt
    -0.39
     combusti
    -0.39
    POSITIVE LOGITS
     Вікі
    0.70
    elemField
    0.70
     الدولى
    0.69
    Datuak
    0.62
    enoord
    0.60
     jsPsych
    0.60
     препратки
    0.57
    âmica
    0.57
     الحره
    0.56
    nationality
    0.56
    Activations Density 3.885%

    No Known Activations