© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118380
    Prev
    Next
    INDEX
    Explanations

    word problems

    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_27_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
     사람
    0.41
    空气
    0.38
     여행
    0.36
     ►
    0.36
     habitation
    0.36
    дые
    0.36
    防災
    0.35
     -----
    0.35
    롱
    0.35
     തുടങ്ങി
    0.34
    POSITIVE LOGITS
    imme
    0.41
     Rou
    0.39
    owing
    0.39
     கூடாது
    0.39
    க்கூடாது
    0.37
    ائم
    0.37
    ^{-\
    0.36
     firstly
    0.36
    emoration
    0.36
    ressa
    0.36
    Activations Density 0.002%

    No Known Activations