© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9514
    Prev
    Next
    INDEX
    Explanations

    words related to human resources and company management

    oai_token-act-pair · gemini-2.0-flash

    Resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     duy
    -0.51
    <eos>
    -0.49
    mpar
    -0.48
    EndTag
    -0.48
     sal
    -0.47
    endal
    -0.46
     Sal
    -0.46
     Par
    -0.44
    хе
    -0.43
     ha
    -0.43
    POSITIVE LOGITS
     myſelf
    0.77
     Efq
    0.75
     Majefty
    0.75
     Monfieur
    0.75
     itſelf
    0.75
     preſent
    0.74
     ſtate
    0.73
     themſelves
    0.73
    ableness
    0.72
    ſelves
    0.70
    Activations Density 8.078%

    No Known Activations