© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242936
    Prev
    Next
    INDEX
    Explanations

    military movement and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    SplashScreen
    0.46
    簇
    0.38
     මි
    0.37
     விநாயக
    0.37
    쿱
    0.36
    incinn
    0.35
    گیری
    0.35
     SplashScreen
    0.35
     giọng
    0.35
    راح
    0.35
    POSITIVE LOGITS
     moviment
    0.40
     rew
    0.39
     move
    0.38
     tow
    0.38
     dement
    0.38
     contro
    0.38
     Molecular
    0.37
     움직
    0.37
    动
    0.37
     reach
    0.36
    Activations Density 0.000%

    No Known Activations