© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67730
    Prev
    Next
    INDEX
    Explanations

    overthrow, deposed, revolution

    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_41_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    넷
    0.44
     ڈاک
    0.43
    〆
    0.39
    ドア
    0.39
     দায়
    0.39
    ewną
    0.38
    নেট
    0.37
    骢
    0.37
     टेक्निकल
    0.36
    命令行
    0.35
    POSITIVE LOGITS
     deposed
    1.87
     deposition
    1.67
     deth
    1.62
     overthrow
    1.61
     depos
    1.59
     overthrown
    1.53
    deposition
    1.41
     dep
    1.41
     depositions
    1.34
     Depos
    1.33
    Activations Density 0.044%

    No Known Activations