© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202359
    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_6_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
     snow
    1.00
     alluvial
    0.98
     î
    0.93
     matériel
    0.92
     ū
    0.91
    एम
    0.91
     truffle
    0.89
     kär
    0.88
     ν
    0.87
     glacial
    0.86
    POSITIVE LOGITS
    m
    1.24
    م
    1.24
    0
    1.19
    ہ
    1.16
    म
    1.10
    рс
    1.07
    ز
    1.05
    ﻭ
    1.02
    ha
    1.00
    ם
    0.99
    Activations Density 0.000%

    No Known Activations