© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 124435
    Prev
    Next
    INDEX
    Explanations

    outperforms or matches other models

    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_37_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
     referring
    0.39
     comparing
    0.38
     describing
    0.37
    𝗈
    0.37
     Expressway
    0.36
    了自己的
    0.36
     கொண்டது
    0.36
     researcher
    0.35
     underwent
    0.35
     researchers
    0.35
    POSITIVE LOGITS
    方法
    0.40
     Properly
    0.38
    操作
    0.38
    خاب
    0.37
     궁
    0.37
     방법
    0.37
     চাহিদা
    0.37
    高く
    0.37
    방법
    0.37
    getVisibility
    0.36
    Activations Density 0.007%

    No Known Activations