© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 37473
    Prev
    Next
    INDEX
    Explanations

    methods and techniques

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     שי
    0.38
     ഉണ്ട
    0.38
     तम
    0.38
     pam
    0.36
     ау
    0.36
     hote
    0.35
    ^{*}=
    0.35
     ہے۔
    0.34
     PTE
    0.34
    られ
    0.34
    POSITIVE LOGITS
     technique
    1.73
     method
    1.58
     methodology
    1.52
     Technique
    1.50
    方法
    1.45
    method
    1.44
     techniques
    1.43
     Method
    1.42
    Method
    1.41
     পদ্ধতি
    1.41
    Activations Density 0.020%

    No Known Activations