© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115946
    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_27_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
     balsam
    0.41
     desempeñ
    0.40
     Analytics
    0.38
     proteolytic
    0.38
     Venom
    0.37
     Collect
    0.37
     quits
    0.37
    슛
    0.36
     Quit
    0.36
     Creat
    0.36
    POSITIVE LOGITS
     हरकत
    0.41
    ِم
    0.37
    ثم
    0.36
    Dim
    0.36
    𝙙
    0.36
    Wil
    0.35
    Доб
    0.35
     मुश्किल
    0.35
     gioco
    0.35
     手
    0.34
    Activations Density 0.000%

    No Known Activations