© 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. 5837
    Prev
    Next
    INDEX
    Explanations

    international affairs and relations

    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
     imitation
    0.51
    halb
    0.41
    σι
    0.41
     aqu
    0.40
    勤
    0.39
     lembut
    0.39
    ческом
    0.38
     Imit
    0.37
     తు
    0.37
    genomen
    0.37
    POSITIVE LOGITS
    anyaan
    0.37
    ASMA
    0.36
    ៣
    0.35
     adhipp
    0.35
    퐈
    0.35
     kil
    0.34
    kil
    0.34
    PTV
    0.34
    Confirm
    0.33
    urée
    0.33
    Activations Density 0.018%

    No Known Activations