© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88602
    Prev
    Next
    INDEX
    Explanations

    opening

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    憨
    0.43
     Backend
    0.37
     séqu
    0.36
    ┣
    0.36
    IÓN
    0.35
    똘
    0.35
    Martha
    0.35
    畈
    0.35
     Dynam
    0.34
    AutoField
    0.34
    POSITIVE LOGITS
    開
    1.86
    开
    1.84
     开
    1.35
     khai
    1.18
     開
    1.11
     opening
    1.03
    が開
    0.91
    opening
    0.89
     Opening
    0.87
    开了
    0.86
    Activations Density 0.003%

    No Known Activations