© 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. 208756
    Prev
    Next
    INDEX
    Explanations

    looking at the viewer

    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
    '><
    0.45
     ses
    0.44
     swim
    0.43
    romyalgia
    0.41
     feat
    0.41
     venit
    0.41
     Cove
    0.41
     Relief
    0.40
     HRV
    0.40
     fondant
    0.40
    POSITIVE LOGITS
     clásico
    0.50
    हू
    0.46
    corto
    0.43
    )$
    0.43
     класи
    0.41
    ₸
    0.41
    ح
    0.41
     clásica
    0.41
    🫢
    0.41
     مختلف
    0.40
    Activations Density 0.001%

    No Known Activations