© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 10092
    Prev
    Next
    INDEX
    Explanations

    Soviet institutes, graduated, education

    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
    枝
    0.39
    慜
    0.36
    ワイ
    0.35
    岩
    0.35
     гимна
    0.35
     पीसीएस
    0.35
    リ
    0.35
    巖
    0.35
     unwind
    0.34
     reserv
    0.34
    POSITIVE LOGITS
     institutes
    0.50
     Institute
    0.49
    Asp
    0.48
     institute
    0.48
     институт
    0.48
     Institutes
    0.46
     INSTITUTE
    0.46
    Institute
    0.45
     Asp
    0.44
     институ
    0.44
    Activations Density 0.026%

    No Known Activations