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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 370
    Prev
    Next
    INDEX
    Explanations

    mentions of the capital letter "S."

    oai_token-act-pair · gemini-2.0-flash

    code and computers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ССР
    -0.60
    haway
    -0.50
    êques
    -0.50
     betweenstory
    -0.49
    infect
    -0.49
    AddHtmlAttribute
    -0.47
     ddelweddau
    -0.47
    انجليز
    -0.47
    anskrit
    -0.47
     argparse
    -0.46
    POSITIVE LOGITS
     excepted
    0.54
     PhpStorm
    0.53
    providedIn
    0.53
    namentales
    0.52
    MADRID
    0.50
     uParam
    0.50
    Portail
    0.50
    󠁢
    0.49
    FontStyle
    0.49
     FetchType
    0.49
    Activations Density 1.038%

    No Known Activations