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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37777
    Prev
    Next
    INDEX
    Explanations

    original text explanations

    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_11_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
    y
    0.44
    ای
    0.30
    .
    0.30
     commutes
    0.29
     ions
    0.28
     investigations
    0.28
    ا
    0.28
     uncertainty
    0.28
    일
    0.27
     increments
    0.27
    POSITIVE LOGITS
     Quadrupèdes
    0.34
     自然
    0.32
    addena
    0.31
    সাহিত্য
    0.31
     ਮੰ
    0.31
     Гра
    0.30
     Fertil
    0.30
     Ги
    0.30
     Держа
    0.30
     Substit
    0.29
    Activations Density 0.257%

    No Known Activations