© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13511
    Prev
    Next
    INDEX
    Explanations

    the word "use" within different contexts

    oai_token-act-pair · gemini-2.0-flash

    use

    np_max-act · gemini-2.0-flash

    ▁Use

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵
    -1.12
     
    -1.05
      
    -0.96
    <eos>
    -0.88
     For
    -0.85
     A
    -0.83
     J
    -0.81
     M
    -0.80
     An
    -0.79
     En
    -0.79
    POSITIVE LOGITS
     Efq
    2.06
     Majefty
    2.02
     purpoſe
    2.02
     myſelf
    2.00
     itſelf
    1.94
     houſe
    1.92
     ſtate
    1.92
     raiſ
    1.91
     Monfieur
    1.88
     pleaſure
    1.86
    Activations Density 1.482%

    No Known Activations