© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173551
    Prev
    Next
    INDEX
    Explanations

    creating html files

    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_20_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
    enum
    0.21
     постави
    0.20
     стратеги
    0.20
     হারানোর
    0.20
    くに
    0.19
    ဥ
    0.19
    Me
    0.19
    ありが
    0.19
     everyday
    0.18
     treb
    0.18
    POSITIVE LOGITS
     utilised
    0.25
     एजेंसी
    0.24
    结
    0.23
    YPE
    0.22
    ائیں
    0.22
     utilise
    0.22
     সম্পন্ন
    0.22
     कराई
    0.22
    伙
    0.22
    aları
    0.22
    Activations Density 0.000%

    No Known Activations