© 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. 2
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    イベント
    0.40
    ())){
    0.39
    événement
    0.38
    گاهی
    0.37
     verdes
    0.36
    フィス
    0.35
    evento
    0.35
    EVENT
    0.35
     tots
    0.34
     DIS
    0.34
    POSITIVE LOGITS
    Bars
    0.42
     सीट
    0.39
     Ern
    0.37
     정사각형
    0.37
     supuesto
    0.37
    ඨ
    0.36
     araştırm
    0.36
     ratios
    0.36
    ����
    0.36
    bars
    0.35
    Activations Density 0.054%

    No Known Activations