© 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. 3772
    Prev
    Next
    INDEX
    Explanations

    references to World War II, specifically the Normandy landings.

    oai_token-act-pair · gemini-2.0-flash

    landing

    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
    onomía
    -0.60
    __':
    -0.57
    WithIOException
    -0.56
    AddTagHelper
    -0.54
    DoubleQuotes
    -0.52
     otomatig
    -0.52
    kháu
    -0.52
     elettrico
    -0.50
    CardHeader
    -0.50
    thenReturn
    -0.50
    POSITIVE LOGITS
     landing
    1.28
     landings
    1.10
    landing
    1.08
    Landing
    1.06
     landed
    1.04
     Landing
    1.01
     desembar
    0.93
     LAND
    0.82
     land
    0.81
     Land
    0.79
    Activations Density 0.522%

    No Known Activations