© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12343
    Prev
    Next
    INDEX
    Explanations

    recent or present symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     schema
    0.38
     characterize
    0.38
     shine
    0.36
    TextUtils
    0.35
     Categories
    0.35
    observe
    0.35
    씀
    0.34
     নেতৃত্ব
    0.34
     Observe
    0.34
     Schema
    0.34
    POSITIVE LOGITS
     \,\
    0.40
     Krank
    0.38
     ഉണ്ടാ
    0.37
     accepté
    0.37
     توجه
    0.36
    ಪಾ
    0.36
     genera
    0.36
    当量
    0.35
     ante
    0.35
     `<`,
    0.34
    Activations Density 0.130%

    No Known Activations