© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197626
    Prev
    Next
    INDEX
    Explanations

    step or profession

    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_50_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
    ಾನೂ
    0.41
     MSM
    0.41
    integration
    0.39
     Endurance
    0.39
     psicología
    0.39
    ﭑ
    0.39
     fécond
    0.38
    烺
    0.38
    באנגלית
    0.38
    мма
    0.37
    POSITIVE LOGITS
    步
    0.79
    职
    0.54
    業
    0.52
     nghiệp
    0.46
    业
    0.44
    職
    0.44
     step
    0.43
    责
    0.43
     paso
    0.42
    ステップ
    0.41
    Activations Density 0.000%

    No Known Activations