© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9955
    Prev
    Next
    INDEX
    Explanations

    new items and concepts

    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_40_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
    ඨ
    0.32
    estable
    0.32
    legiate
    0.31
    ☎
    0.31
    レビ
    0.31
     मॉर्निंग
    0.31
    éci
    0.31
    elio
    0.31
     estable
    0.30
    碓
    0.30
    POSITIVE LOGITS
     new
    3.14
    new
    2.84
     নতুন
    2.67
     новые
    2.45
     новых
    2.45
     neuen
    2.44
     nieuwe
    2.41
     nueva
    2.39
     جديد
    2.39
     yeni
    2.39
    Activations Density 0.158%

    No Known Activations