© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250909
    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_56_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
     thể
    0.40
     체
    0.39
    體
    0.39
     HAB
    0.37
    ුවන්
    0.37
    wegen
    0.36
    ビー
    0.36
    체
    0.35
     کبھی
    0.35
    গ্রাফ
    0.35
    POSITIVE LOGITS
     i
    0.49
     capt
    0.44
     welcome
    0.43
    になり
    0.43
    된
    0.43
     ex
    0.40
     Welcome
    0.40
     became
    0.40
    欢迎
    0.39
     captivated
    0.39
    Activations Density 0.000%

    No Known Activations