© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203700
    Prev
    Next
    INDEX
    Explanations

    famine and grains

    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_37_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
    麂
    0.44
    ╝
    0.40
    沉
    0.39
     estadounid
    0.39
     солнца
    0.38
    蘚
    0.37
    痠
    0.36
    俥
    0.35
    
    0.35
    tram
    0.34
    POSITIVE LOGITS
     wheat
    1.11
     grain
    1.09
     rice
    0.99
    Wheat
    0.98
    wheat
    0.96
     grains
    0.96
     maize
    0.96
     Grain
    0.96
    Grain
    0.96
    小麦
    0.94
    Activations Density 0.002%

    No Known Activations