© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110223
    Prev
    Next
    INDEX
    Explanations

    World War and Interwar Period

    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_2_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
    к
    1.09
    تها
    1.06
    thed
    1.01
    м
    0.95
    هُ
    0.90
    ке
    0.86
     зависимости
    0.84
    تين
    0.83
    б
    0.82
    };
    0.82
    POSITIVE LOGITS
    ir
    1.59
    ra
    1.42
    ва
    1.39
    j
    1.38
    re
    1.34
    it
    1.34
    I
    1.30
     I
    1.28
    ed
    1.26
     by
    1.24
    Activations Density 0.001%

    No Known Activations