© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130814
    Prev
    Next
    INDEX
    Explanations

    Bolsheviks and Kremlin referring to Russia

    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
    ك
    1.55
    у
    1.38
    д
    1.34
    и
    1.30
    й
    1.27
     ότι
    1.25
    з
    1.23
    quela
    1.23
    ро
    1.19
    г
    1.17
    POSITIVE LOGITS
     J
    1.01
     Aerospace
    0.93
     Fractional
    0.91
     B
    0.91
     V
    0.91
    ಾಲ
    0.90
     T
    0.89
    ارس
    0.88
    ۰
    0.88
     Karm
    0.87
    Activations Density 0.001%

    No Known Activations