© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196967
    Prev
    Next
    INDEX
    Explanations

    verbal cues

    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_27_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
    语法
    0.37
     مالی
    0.36
     COM
    0.35
     Сасик
    0.35
     سانس
    0.34
    誅
    0.34
     militar
    0.33
    艺术家
    0.33
    蹂
    0.33
    прият
    0.33
    POSITIVE LOGITS
    лем
    0.37
    nul
    0.34
     ئەو
    0.34
     whenever
    0.33
     Pue
    0.33
     expresa
    0.33
    đe
    0.33
     oral
    0.33
     devotion
    0.32
     excess
    0.32
    Activations Density 0.003%

    No Known Activations