© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11703
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to manufacturing processes, chemical processes, and semiconductor device fabrication in technical documentation

    oai_token-act-pair · gemini-2.0-flash

    process

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     process
    -2.47
     Process
    -2.36
    Process
    -2.28
    process
    -2.23
     PROCESS
    -2.08
     processes
    -2.05
     Processes
    -1.98
    processes
    -1.88
    PROCESS
    -1.84
    Processes
    -1.75
    POSITIVE LOGITS
    期刊论文
    0.58
    SuppressLint
    0.57
     pinulongan
    0.57
     ddelweddau
    0.54
    
    0.53
    cách
    0.51
    MathML
    0.51
    🟤
    0.51
     WaitForSeconds
    0.51
    oser
    0.50
    Activations Density 6.531%

    No Known Activations