© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14004
    Prev
    Next
    INDEX
    Explanations

    place names, especially in Ireland, China, or the United States

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    tagHelperRunner
    -0.73
     تضيفلها
    -0.65
    ConstraintMaker
    -0.64
     Chwiliwch
    -0.63
    SequentialGroup
    -0.62
    Tikang
    -0.59
     صوتيه
    -0.59
     informée
    -0.59
    RegressionTest
    -0.58
    oredCriteria
    -0.57
    POSITIVE LOGITS
     StatelessWidget
    0.55
    TacToe
    0.55
     StatefulWidget
    0.50
     Calling
    0.47
    ும்
    0.44
    <>(
    0.44
    AttributeSet
    0.44
     NUKAT
    0.44
    intracht
    0.44
    Subviews
    0.42
    Activations Density 1.809%

    No Known Activations