© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155930
    Prev
    Next
    INDEX
    Explanations

    battlefield or military operations

    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_50_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
     sea
    0.55
    moh
    0.42
    Sea
    0.41
     Seah
    0.40
     সড়ক
    0.40
     electron
    0.40
     robo
    0.39
    侑
    0.39
    樂
    0.38
     IS
    0.38
    POSITIVE LOGITS
    exploration
    0.42
    Navigation
    0.42
     Field
    0.42
     Navigation
    0.42
     ग्राउंड
    0.41
    navigation
    0.41
     Expedition
    0.41
     navegación
    0.40
    anthin
    0.40
    Field
    0.39
    Activations Density 0.009%

    No Known Activations