© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9639
    Prev
    Next
    INDEX
    Explanations

    dining, cup, steak, or champagne

    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_40_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
    готов
    0.37
     Fertilizer
    0.36
    렷
    0.36
    ране
    0.33
    fertil
    0.33
     ڈی
    0.33
     rosem
    0.33
    굉
    0.33
    かり
    0.33
    >.
    0.33
    POSITIVE LOGITS
     Champagne
    0.55
     champagne
    0.50
    水晶
    0.40
    Sandra
    0.40
     champ
    0.38
    Champ
    0.38
     cutting
    0.37
     fragility
    0.37
    Referring
    0.36
    champ
    0.36
    Activations Density 0.061%

    No Known Activations