© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139242
    Prev
    Next
    INDEX
    Explanations

    translating Japanese

    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_12_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
     termites
    0.57
     দ
    0.57
     komple
    0.54
     jiné
    0.54
     eléctricas
    0.54
    рот
    0.53
     маршру
    0.52
     冖
    0.52
     regiments
    0.52
     hordes
    0.51
    POSITIVE LOGITS
    m
    0.75
    in
    0.71
    i
    0.56
    ،
    0.55
    is
    0.55
    、
    0.54
    inic
    0.52
    om
    0.51
    ினேன்
    0.50
    aspir
    0.49
    Activations Density 0.007%

    No Known Activations