© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101073
    Prev
    Next
    INDEX
    Explanations

    income inequality

    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_16_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
    ྜ
    0.55
    reality
    0.52
    Reality
    0.52
    ╭
    0.52
    
    0.50
     enmity
    0.50
     Campus
    0.49
    棍
    0.49
    牪
    0.49
    られる
    0.48
    POSITIVE LOGITS
     institu
    0.55
     has
    0.51
     telah
    0.50
    Ъ
    0.50
     used
    0.50
     insurer
    0.49
    STIT
    0.48
     spur
    0.48
    ARIA
    0.47
     ஸ்
    0.47
    Activations Density 0.016%

    No Known Activations