© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52329
    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_30_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
    告诉
    0.39
    training
    0.38
    ванные
    0.38
     प्रार्थना
    0.37
    fellow
    0.37
    ০১
    0.36
    仮
    0.36
    azines
    0.35
    thanks
    0.35
    izzard
    0.35
    POSITIVE LOGITS
    墳
    0.37
     quenched
    0.37
     위하여
    0.36
     beeld
    0.36
     visitation
    0.35
     zusätzliche
    0.35
    Kalb
    0.35
     cubic
    0.35
     পুনর্ব
    0.35
     apothe
    0.35
    Activations Density 0.000%

    No Known Activations