© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51178
    Prev
    Next
    INDEX
    Explanations

    Soviet and Russian figures and terms

    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_31_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
     درج
    0.38
     grade
    0.37
     NF
    0.36
     गा
    0.36
     motif
    0.35
    rát
    0.35
    懂
    0.33
    ாது
    0.33
    DWARF
    0.32
     чтения
    0.32
    POSITIVE LOGITS
     коммуника
    0.41
     Евро
    0.40
    ёг
    0.39
    鎊
    0.39
    Disposable
    0.38
     लोकेशन
    0.38
    levision
    0.38
     Brus
    0.37
    NewLabel
    0.37
     αποτε
    0.37
    Activations Density 0.000%

    No Known Activations