© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21023
    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_56_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
    油
    1.25
     oil
    1.08
     油
    1.00
    Oil
    0.98
    oil
    0.98
     Oil
    0.96
     OIL
    0.83
     ऑयल
    0.83
     तेल
    0.79
     масло
    0.78
    POSITIVE LOGITS
    都
    0.75
     都
    0.63
    こちら
    0.53
    こちらの
    0.46
    臨
    0.44
    こちらは
    0.40
    根
    0.39
     ResourceManager
    0.39
    都已经
    0.38
     Hing
    0.37
    Activations Density 0.041%

    No Known Activations