© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12652
    Prev
    Next
    INDEX
    Explanations

    words related to corporate and political leadership

    oai_token-act-pair · gemini-2.0-flash

    executive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -2.53
     Executive
    -2.45
    Executive
    -2.41
    executive
    -2.22
     EXECUTIVE
    -2.19
    EXECUTIVE
    -1.98
     Executives
    -1.80
     Exec
    -1.76
     exec
    -1.67
     executives
    -1.65
    POSITIVE LOGITS
     referenties
    0.56
     Steady
    0.51
    beni
    0.49
    ReusableCell
    0.49
     ${({
    0.48
    EClass
    0.47
    PyErr
    0.47
    JpaRepository
    0.46
    steady
    0.46
     getBase
    0.45
    Activations Density 6.144%

    No Known Activations