© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11811
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions followed by nouns describing locations

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     parlent
    -0.46
     betrek
    -0.44
     isolamento
    -0.44
     femininos
    -0.43
     Hinsicht
    -0.43
     risorse
    -0.42
     femininas
    -0.42
     gebouwd
    -0.41
     unele
    -0.41
     esfuer
    -0.40
    POSITIVE LOGITS
    хьтан
    0.73
    HasAnnotation
    0.73
     StatefulWidget
    0.72
     pageContext
    0.70
    tagext
    0.68
     other
    0.66
     kasarigan
    0.65
    abestanden
    0.65
    DeleteBehavior
    0.65
    клопе
    0.65
    Activations Density 0.646%

    No Known Activations