© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43964
    Prev
    Next
    INDEX
    Explanations

    file types: TXT

    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_13_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
    ле
    0.22
    ती
    0.22
    fromi
    0.22
     Spell
    0.21
    ו
    0.21
     Emperor
    0.20
    otro
    0.20
    י
    0.20
    e
    0.20
     Word
    0.20
    POSITIVE LOGITS
    ختلف
    0.20
     രീതി
    0.20
    ديث
    0.19
     которы
    0.19
    ੍ਰ
    0.19
     方法
    0.18
     μεταξύ
    0.18
    dB
    0.18
    Ⲏ
    0.18
     送料無料
    0.18
    Activations Density 0.004%

    No Known Activations