© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217362
    Prev
    Next
    INDEX
    Explanations

    geographic or political regions

    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_31_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
     naz
    0.34
     attention
    0.33
     infinitely
    0.33
    naz
    0.33
     sham
    0.32
    ring
    0.31
    훨
    0.31
     string
    0.31
     wid
    0.31
     bars
    0.31
    POSITIVE LOGITS
    顐
    0.40
    跇
    0.40
     ஏற்ற
    0.38
    䨘
    0.38
     Pick
    0.37
    ភាព
    0.37
    TintColor
    0.37
    」（
    0.36
    దారు
    0.36
    ণ্
    0.35
    Activations Density 0.002%

    No Known Activations