© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82490
    Prev
    Next
    INDEX
    Explanations

    Russian suffixes

    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_53_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
    庿
    0.40
    㢦
    0.38
    DomainMask
    0.38
    ลา
    0.37
    chloric
    0.37
     sqlite
    0.36
    vrage
    0.36
    новой
    0.35
    縦
    0.35
    
    0.35
    POSITIVE LOGITS
    ень
    1.36
    рень
    1.09
    лень
    1.09
    жень
    0.95
    день
    0.95
    шень
    0.85
    чень
    0.79
    нь
    0.72
    ień
    0.70
    пень
    0.68
    Activations Density 0.001%

    No Known Activations