© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3892
    Prev
    Next
    INDEX
    Explanations

    words and phrases specific to American professional sports

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    isContained
    -0.60
    makeConstraints
    -0.59
    HandlerContext
    -0.58
     aDecoder
    -0.54
     nato
    -0.53
    ặc
    -0.51
    kaŭ
    -0.50
    SizeMode
    -0.50
     eventdata
    -0.50
     alış
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.55
    íqu
    0.54
    Odkazy
    0.51
     '\\;'
    0.49
    hoeddwyd
    0.49
     válvulas
    0.48
    provisional
    0.48
     enlaces
    0.47
    Rujukan
    0.47
     kaarangay
    0.47
    Activations Density 13.728%

    No Known Activations