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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14871
    Prev
    Next
    INDEX
    Explanations

    the prefix "mus" (likely as part of medical terms or usernames)

    oai_token-act-pair · gemini-2.0-flash

    Mus/mus

    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
     ویکی‌پدیا
    -0.63
    setVerticalGroup
    -0.60
    HasForeignKey
    -0.59
    MigrationBuilder
    -0.58
    ngrx
    -0.56
    InjectAttribute
    -0.55
    ollection
    -0.54
     оригіналу
    -0.52
     AppCompatTheme
    -0.52
     Signalez
    -0.51
    POSITIVE LOGITS
     thủ
    0.47
     jsPsych
    0.45
     Thủ
    0.45
    oneofs
    0.44
    su
    0.44
    مصادر
    0.43
    sor
    0.42
    ffet
    0.42
    州市
    0.41
    skat
    0.41
    Activations Density 0.225%

    No Known Activations