© 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. 3051
    Prev
    Next
    INDEX
    Explanations

    the word "qualified" or words related to qualification

    oai_token-act-pair · gemini-2.0-flash

    qualified

    np_max-act · gemini-2.0-flash

    qualified

    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
     
    -1.15
    <strong>
    -0.89
     “
    -0.88
     (
    -0.88
     a
    -0.87
    ↵↵
    -0.79
    <em>
    -0.78
     in
    -0.78
    1
    -0.77
      
    -0.76
    POSITIVE LOGITS
     Monfieur
    1.34
    ſelf
    1.34
     Eſ
    1.32
     Majefty
    1.30
     Efq
    1.30
     Jefus
    1.29
    RenderAtEndOf
    1.27
    ſelves
    1.27
     Diſ
    1.22
     itſelf
    1.21
    Activations Density 1.514%

    No Known Activations