© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 21799
    Prev
    Next
    INDEX
    Explanations

    action

    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_56_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
     ді
    1.79
    ді
    1.02
     dz
    0.96
     الف
    0.94
     Ді
    0.87
     del
    0.83
     δ
    0.82
     дзе
    0.81
     F
    0.79
    DZ
    0.78
    POSITIVE LOGITS
     действу
    0.73
     дей
    0.72
     действует
    0.59
     പ്രവർത്തന
    0.58
    activities
    0.55
     செயற்ப
    0.55
     പ്രവര്‍ത്തന
    0.55
     പ്രവര്‍ത്തി
    0.54
     പ്രവർ
    0.52
    활동
    0.52
    Activations Density 0.012%

    No Known Activations