© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197984
    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_50_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
     Ned
    0.42
    magnet
    0.42
    Ned
    0.41
    Magnet
    0.41
    kable
    0.41
     Aline
    0.40
     magnetism
    0.40
    }_{{\
    0.39
    Diagonal
    0.39
    રે
    0.38
    POSITIVE LOGITS
     COMM
    0.40
    emers
    0.39
     judgment
    0.39
     rootView
    0.38
     рода
    0.37
     数
    0.36
     mev
    0.36
     निया
    0.36
    ungunya
    0.36
     traction
    0.36
    Activations Density 0.000%

    No Known Activations