© 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. 242769
    Prev
    Next
    INDEX
    Explanations

    protests, riots, demonstrations, scandal

    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
     인천
    0.43
    Pert
    0.39
     শিশুরা
    0.39
     Clusters
    0.39
     insects
    0.39
    जेक्शन
    0.38
     Incident
    0.37
     병
    0.37
    Incident
    0.37
     Pert
    0.36
    POSITIVE LOGITS
     roadblocks
    0.53
     riots
    0.49
     riot
    0.46
     roadblock
    0.45
     road
    0.44
     bus
    0.44
     recall
    0.43
     demonstration
    0.43
    riots
    0.43
     scandal
    0.42
    Activations Density 0.035%

    No Known Activations