© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 613
    Prev
    Next
    INDEX
    Explanations

    specifications for boats, especially speed ("knots") and equipment ("engines")

    oai_token-act-pair · gemini-2.0-flash

    Boat speed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     walls
    -0.82
     wall
    -0.82
    Wall
    -0.80
     Wall
    -0.79
    wall
    -0.76
     Walls
    -0.72
     WALL
    -0.71
     المعيارى
    -0.71
    ContentLoaded
    -0.69
    ]")]
    -0.69
    POSITIVE LOGITS
     تضيفلها
    0.62
     helm
    0.50
     stiefel
    0.47
     Schwert
    0.44
     fören
    0.44
    Билгалдахарш
    0.44
     bow
    0.43
     ponts
    0.42
    quête
    0.42
     passée
    0.42
    Activations Density 0.768%

    No Known Activations