© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30666
    Prev
    Next
    INDEX
    Explanations

    Scripting and data structures

    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
    Invoke
    0.43
    ویر
    0.40
     تفسیر
    0.38
     해석
    0.37
    edit
    0.37
     vectorize
    0.36
    ூல்
    0.35
    ፈ
    0.35
    对象
    0.35
    Fragmentation
    0.34
    POSITIVE LOGITS
     Script
    0.87
     script
    0.84
    Script
    0.76
    script
    0.67
     स्क्रिप्ट
    0.67
    脚本
    0.65
     scripts
    0.64
     Scripts
    0.61
    Scripts
    0.59
    SCRIPT
    0.59
    Activations Density 0.115%

    No Known Activations