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. 14337
    Prev
    Next
    INDEX
    Explanations

    numerical sequences that appear to be dates, times and code files

    oai_token-act-pair · gemini-2.0-flash

    Ordinal numbers

    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
     Wednesday
    -0.67
     Tuesday
    -0.67
    Tuesday
    -0.60
    Wednesday
    -0.59
     terça
    -0.55
     mercredi
    -0.54
     WEDNESDAY
    -0.53
    3
    -0.50
     mardi
    -0.50
     '../
    -0.48
    POSITIVE LOGITS
     sixth
    1.03
     seventh
    1.00
     Satur
    0.94
     Seventh
    0.92
     Sixth
    0.90
     SIX
    0.89
    rrggbb
    0.88
     GenerationType
    0.87
     Paglinawan
    0.85
     Exactos
    0.84
    Activations Density 4.620%

    No Known Activations