© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197429
    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
     ಅವರನ್ನು
    0.47
     ਤਾਂ
    0.43
     격
    0.41
    animity
    0.40
     متن
    0.40
     범
    0.40
    m
    0.40
    ವಾಗಿದೆ
    0.39
     කො
    0.39
    였
    0.39
    POSITIVE LOGITS
    oloji
    0.49
    ειας
    0.48
    Nombre
    0.47
    Huang
    0.47
     ulter
    0.47
    يارات
    0.47
    гром
    0.46
     passeio
    0.46
    Hat
    0.46
    לות
    0.46
    Activations Density 0.000%

    No Known Activations