© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129810
    Prev
    Next
    INDEX
    Explanations

    Russian verb endings

    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_1_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
    ia
    0.75
    на
    0.71
    тно
    0.68
    ки
    0.66
    ag
    0.60
     الع
    0.60
    0
    0.59
     للأ
    0.57
    م
    0.56
    他的
    0.55
    POSITIVE LOGITS
    ED
    1.08
    ي
    1.00
    ET
    0.89
    UR
    0.85
     blistering
    0.83
    ่า
    0.82
    də
    0.80
    ٣
    0.79
     cranial
    0.78
    ]
    0.76
    Activations Density 0.000%

    No Known Activations