© 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. 10938
    Prev
    Next
    INDEX
    Explanations

    terms relating to political and military conflict and division

    oai_token-act-pair · gemini-2.0-flash

    split

    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
     split
    -2.31
     Split
    -2.13
    split
    -2.03
    Split
    -1.98
     splits
    -1.93
     divided
    -1.91
     splitting
    -1.88
     divide
    -1.83
     dividing
    -1.73
     division
    -1.71
    POSITIVE LOGITS
     lccn
    0.51
    arial
    0.49
     AssemblyProduct
    0.49
    artifactId
    0.48
     فريبيس
    0.47
    URB
    0.46
     uintptr
    0.45
    viale
    0.44
    ಂದ
    0.44
    EventLoop
    0.44
    Activations Density 17.718%

    No Known Activations