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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8202
    Prev
    Next
    INDEX
    Explanations

    translatable concept

    np_acts-logits-general · gemini-2.5-flash-lite

    trans- prefix followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🧣
    0.42
    育成
    0.36
     በፍ
    0.34
    妑
    0.34
    ampion
    0.33
    оні
    0.33
    淞
    0.33
    缰
    0.33
    匍
    0.32
    chnik
    0.32
    POSITIVE LOGITS
     Trans
    4.59
    Trans
    4.50
    trans
    4.38
     trans
    4.31
     тран
    3.92
     TRANS
    3.91
     ट्रांस
    3.80
    TRANS
    3.67
     транс
    3.67
     Тран
    3.58
    Activations Density 0.221%

    No Known Activations