© 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. 9796
    Prev
    Next
    INDEX
    Explanations

    words related to management roles or organizations

    oai_token-act-pair · gemini-2.0-flash

    business and code contexts

    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
     executive
    -1.85
     Executive
    -1.83
    Executive
    -1.74
     exec
    -1.68
    executive
    -1.66
     EXECUTIVE
    -1.63
     Exec
    -1.63
    exec
    -1.54
     board
    -1.54
    EXECUTIVE
    -1.52
    POSITIVE LOGITS
     StatefulWidget
    0.60
    
    0.59
    DataSetChanged
    0.54
     Papers
    0.49
    Papers
    0.48
    ագրություն
    0.47
    ūsu
    0.47
    ̍t
    0.45
    脚注の使い方
    0.45
    }")
    0.44
    Activations Density 1.965%

    No Known Activations