© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197118
    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
     তোমার
    0.38
    袮
    0.38
     Woman
    0.37
    려는
    0.36
     Preservation
    0.35
    ﻦ
    0.35
    growth
    0.35
     Conversations
    0.35
    
    0.34
     folklor
    0.34
    POSITIVE LOGITS
     घोष
    0.46
     역시
    0.43
     consigo
    0.43
     masing
    0.42
    ഘ
    0.42
     degrés
    0.38
     termos
    0.37
     entweder
    0.37
     perangkat
    0.37
     整
    0.37
    Activations Density 0.000%

    No Known Activations