© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10215
    Prev
    Next
    INDEX
    Explanations

    the word "to" coupled with words implying duty, obligation, or legal rights

    oai_token-act-pair · gemini-2.0-flash

    words ending in -ation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     fumée
    -0.61
     genoux
    -0.58
     leçon
    -0.58
     nôtre
    -0.57
     dignité
    -0.51
     circunstancia
    -0.49
    NameInMap
    -0.47
     légiti
    -0.47
     planète
    -0.46
     graisse
    -0.46
    POSITIVE LOGITS
     separation
    0.95
     oxidation
    0.94
     condemnation
    0.92
     colonization
    0.91
     quantization
    0.90
     stimulation
    0.90
     sterilization
    0.90
     stabilization
    0.90
     installation
    0.89
     prosecution
    0.89
    Activations Density 19.057%

    No Known Activations