© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40391
    Prev
    Next
    INDEX
    Explanations

    Russian words

    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_57_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
     așa
    0.71
     și
    0.68
     perchè
    0.65
     ț
    0.64
    և
    0.61
     Și
    0.60
    および
    0.58
     oraș
    0.58
     traveler
    0.57
     față
    0.57
    POSITIVE LOGITS
    cciona
    0.38
    льку
    0.36
    (/(
    0.36
     Balls
    0.35
     бол
    0.35
     cxb
    0.35
    
    0.35
    ূলক
    0.34
    „
    0.33
    幕
    0.33
    Activations Density 0.001%

    No Known Activations