© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4664
    Prev
    Next
    INDEX
    Explanations

    descriptions of air combat in World War 2

    oai_token-act-pair · gemini-2.0-flash

    Military squadrons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     intptr
    -0.51
    SequentialGroup
    -0.50
    ium
    -0.49
    ride
    -0.47
    encodeWith
    -0.46
     thiệu
    -0.46
     broader
    -0.43
    nants
    -0.43
    parseFrom
    -0.43
    BRACE
    -0.43
    POSITIVE LOGITS
     NavController
    0.87
    #+#
    0.87
     noDo
    0.66
     EconPapers
    0.64
    +#+#
    0.63
    Demografie
    0.62
    AntiForgeryToken
    0.61
     الدولى
    0.61
    цездатний
    0.60
     nonUne
    0.60
    Activations Density 1.429%

    No Known Activations