© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216614
    Prev
    Next
    INDEX
    Explanations

    mixed language or unusual characters

    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_16_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
    heim
    0.48
    impi
    0.47
    ROC
    0.46
    9
    0.46
    ocalization
    0.46
    ッチン
    0.45
     polarization
    0.45
     feeding
    0.45
    ሪያ
    0.44
    微
    0.43
    POSITIVE LOGITS
     Еўро
    0.56
     Tell
    0.54
    åll
    0.52
     Similarity
    0.52
     Еўропы
    0.52
     Compress
    0.50
     Sử
    0.50
    搆
    0.50
     épouse
    0.49
    놁
    0.49
    Activations Density 0.000%

    No Known Activations