© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    mentions of Israel and the Israeli military

    oai_token-act-pair · gemini-2.0-flash

    Israel

    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
    <bos>
    -1.52
     Israel
    -1.16
    Israel
    -1.09
     Israeli
    -0.86
    Israeli
    -0.80
     Israël
    -0.73
    israel
    -0.70
     ISRAEL
    -0.69
     israel
    -0.69
    以色列
    -0.60
    POSITIVE LOGITS
    EDEFAULT
    0.87
    yship
    0.74
    DotNetBar
    0.71
    IonicModule
    0.69
    getRuntime
    0.69
    ArgumentParser
    0.69
    UserScript
    0.68
     MainAxisSize
    0.68
    interopRequire
    0.67
     externi
    0.66
    Activations Density 0.223%

    No Known Activations