© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64424
    Prev
    Next
    INDEX
    Explanations

    wars

    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_46_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
     ১৯৯
    0.48
     ’
    0.46
     ১৯৮
    0.42
     बुद्ध
    0.38
    ."'
    0.38
     ۱۹
    0.37
    ২০০
    0.37
     ২০০
    0.36
    sce
    0.36
     ভারতকে
    0.36
    POSITIVE LOGITS
     placed
    0.38
     bombings
    0.37
     pacing
    0.36
    兵
    0.35
    ayson
    0.35
    είς
    0.35
     bombed
    0.35
     paced
    0.34
    Ry
    0.34
    یرے
    0.34
    Activations Density 0.008%

    No Known Activations