© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15508
    Prev
    Next
    INDEX
    Explanations

    instances of the word "count" and nearby mathematical symbols, code snippets, table names, and field names

    oai_token-act-pair · gemini-2.0-flash

    count

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     count
    -1.83
     Count
    -1.64
    count
    -1.60
    Count
    -1.57
     COUNT
    -1.50
     counts
    -1.50
    COUNT
    -1.38
     Counts
    -1.33
     counted
    -1.33
    counts
    -1.29
    POSITIVE LOGITS
    ONSORED
    0.59
     mực
    0.57
     Yew
    0.57
     كومونز
    0.55
     Explora
    0.54
     getRequest
    0.54
    ragan
    0.54
     referenties
    0.54
     Manch
    0.54
     ―――――
    0.52
    Activations Density 35.617%

    No Known Activations