© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6590
    Prev
    Next
    INDEX
    Explanations

    descriptions comparing two entities in terms of weapon use and combat abilities

    oai_token-act-pair · gemini-2.0-flash

    opponents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ритори
    -0.57
    Dichloroethane
    -0.56
     الرياضيه
    -0.50
    windowFixed
    -0.49
    memoized
    -0.48
    HttpSession
    -0.47
    ագրություններ
    -0.47
     otomatig
    -0.45
    sbin
    -0.44
    mergeFrom
    -0.44
    POSITIVE LOGITS
     opponent
    2.20
     opposition
    2.14
     opposing
    2.03
     opponents
    2.03
     enemy
    2.00
    opponent
    1.79
    opposition
    1.76
    Opposition
    1.73
     adversary
    1.72
     Opposition
    1.70
    Activations Density 0.909%

    No Known Activations