© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11666
    Prev
    Next
    INDEX
    Explanations

    text about air conditioning systems

    oai_token-act-pair · gemini-2.0-flash

    conditioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    argout
    -0.87
    sizeCache
    -0.75
     الرياضيه
    -0.74
     فريبيس
    -0.74
     <",
    -0.70
    TagHelpers
    -0.70
    WebServlet
    -0.69
    issory
    -0.69
     imageNamed
    -0.68
    MemoryWarning
    -0.67
    POSITIVE LOGITS
    <bos>
    0.79
    he
    0.41
    
    0.38
    a
    0.38
    tan
    0.37
     eventually
    0.36
     ab
    0.35
    Ab
    0.35
    Acc
    0.34
     acela
    0.34
    Activations Density 0.899%

    No Known Activations