© 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. 244515
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

    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
     attempts
    0.42
    ამართ
    0.41
     Environment
    0.40
     ಸಂಗ
    0.38
    嘻
    0.37
    لاسه
    0.36
     Empresa
    0.36
    Base
    0.36
    有名な
    0.36
    Component
    0.36
    POSITIVE LOGITS
    தெ
    0.43
    ɣ
    0.38
     Executes
    0.37
    (()=>{
    0.36
    幸
    0.35
     ദുൽ
    0.35
     ठ
    0.35
     [][]
    0.34
    ßer
    0.34
    ði
    0.34
    Activations Density 0.006%

    No Known Activations