© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7554
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in technical documentation or patents

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to fabrication and metal processes

    np_token-act-pair-logits · gpt-4o-mini

    material processing/manufacturing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     feroit
    -0.85
     dieux
    -0.82
     enfans
    -0.82
     Efq
    -0.82
     fédé
    -0.82
     becauſe
    -0.79
     Theſe
    -0.78
     uſed
    -0.78
     étoit
    -0.76
     démocr
    -0.76
    POSITIVE LOGITS
    ,
    0.70
     L
    0.58
     Pat
    0.55
      
    0.52
     true
    0.50
     O
    0.49
     
    0.48
     Reverso
    0.47
    iotensin
    0.47
     single
    0.47
    Activations Density 23.017%

    No Known Activations