© 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. 4027
    Prev
    Next
    INDEX
    Explanations

    corneal edema and dry eyes

    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
    াহতি
    0.45
     фонд
    0.39
     Talbot
    0.36
     chocol
    0.36
    指向
    0.36
    遌
    0.36
    基金
    0.35
    trailing
    0.35
    ໑
    0.35
     Selector
    0.34
    POSITIVE LOGITS
     corneal
    1.13
     Corne
    1.11
     cornea
    1.09
     corne
    1.08
    Cor
    1.01
     кор
    0.97
     COR
    0.94
     kor
    0.92
    cor
    0.89
     cor
    0.89
    Activations Density 0.027%

    No Known Activations