© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11232
    Prev
    Next
    INDEX
    Explanations

    words related to military defense and sports offense

    oai_token-act-pair · gemini-2.0-flash

    defensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ich
    -0.88
     ich
    -0.82
     defensive
    -0.73
    ICH
    -0.70
    lich
    -0.67
    les
    -0.65
     Ich
    -0.64
    Eth
    -0.64
    Ich
    -0.64
     Defensive
    -0.63
    POSITIVE LOGITS
    ImageContext
    0.82
    WebServlet
    0.69
     Merrick
    0.63
    UAWEI
    0.61
    AndroidJUnit
    0.61
    anghai
    0.61
    ExecuteReader
    0.60
    farin
    0.60
     Houſe
    0.60
    xFFFFFF
    0.59
    Activations Density 3.200%

    No Known Activations