© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3948
    Prev
    Next
    INDEX
    Explanations

    mentions of rockets, missiles, and rocket fuel.

    oai_token-act-pair · gemini-2.0-flash

    missiles and fuel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     InputDecoration
    -0.97
    tvguidetime
    -0.95
     estekak
    -0.94
    MessageTagHelper
    -0.93
    TypedDataSet
    -0.91
     nahilalakip
    -0.88
    PerformLayout
    -0.87
     שוליים
    -0.84
    InstrumentedTest
    -0.77
    новништво
    -0.76
    POSITIVE LOGITS
     rocket
    0.60
     SpaceX
    0.49
    Future
    0.48
     rockets
    0.47
    火箭
    0.47
    arrow
    0.46
     Future
    0.46
     bolig
    0.45
    yanka
    0.43
    bals
    0.43
    Activations Density 0.875%

    No Known Activations