© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158382
    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
    anii
    0.41
     tib
    0.39
     An
    0.39
     Mandel
    0.39
     Tiber
    0.39
    シス
    0.38
     ویت
    0.37
    ᓯ
    0.36
    hesis
    0.35
     tibia
    0.35
    POSITIVE LOGITS
    Lak
    0.41
    ướ
    0.39
    Bened
    0.39
    LAGAB
    0.39
    MBA
    0.39
     फाय
    0.38
    LoggerFactory
    0.38
    blockList
    0.38
    grunt
    0.38
    FAs
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.