© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44212
    Prev
    Next
    INDEX
    Explanations

    Opium Wars

    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_3_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
     and
    0.73
    тах
    0.64
    of
    0.63
    ная
    0.61
    stof
    0.61
     or
    0.59
     renormal
    0.59
    骓
    0.59
    вань
    0.58
    ੰ
    0.58
    POSITIVE LOGITS
     in
    1.09
    在
    0.94
    .
    0.81
    し
    0.80
    ใน
    0.80
     في
    0.71
    ని
    0.69
    ש
    0.68
    a
    0.68
     σε
    0.66
    Activations Density 0.003%

    No Known Activations