© 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-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146764
    Prev
    Next
    INDEX
    Explanations

    war

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     قاف
    0.37
    Vod
    0.36
     interv
    0.34
    Undo
    0.32
    દય
    0.32
     Undo
    0.32
    奮
    0.32
     ύ
    0.32
    erus
    0.32
     bohat
    0.31
    POSITIVE LOGITS
     war
    3.64
     War
    2.81
    war
    2.81
    War
    2.70
    战
    2.53
    戦
    2.47
    戰
    2.22
     جنگ
    2.08
     война
    2.08
     الحرب
    2.00
    Activations Density 0.049%

    No Known Activations