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. 16199
    Prev
    Next
    INDEX
    Explanations

    career and position titles, especially in academia.

    oai_token-act-pair · gemini-2.0-flash

    Biography or description of people

    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
    fromnode
    -1.01
    yntaxException
    -0.98
     <>",
    -0.91
     GenerationType
    -0.90
     AssemblyCompany
    -0.82
    IsMutable
    -0.82
    saraba
    -0.77
    ,:);
    -0.76
    SBATCH
    -0.76
     تضيفلها
    -0.73
    POSITIVE LOGITS
    section
    0.42
    tert
    0.39
     disposición
    0.39
    je
    0.39
     joy
    0.38
     nazionali
    0.38
     bianche
    0.37
    Po
    0.37
     happy
    0.36
    UMEN
    0.35
    Activations Density 0.763%

    No Known Activations