© 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
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 195522
    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_26_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
    のお
    0.43
     확
    0.42
    抜け
    0.42
     dep
    0.41
     مالی
    0.41
     جسم
    0.40
    外
    0.40
    令
    0.40
    льтра
    0.39
     کسی
    0.39
    POSITIVE LOGITS
    𝐊
    0.54
    মুখি
    0.52
    🎲
    0.52
     Omphalodes
    0.51
    мл
    0.50
    𝐅
    0.50
    iziert
    0.49
    ιουργ
    0.49
    क्रोश
    0.49
    ………….
    0.48
    Activations Density 0.000%

    No Known Activations