© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30338
    Prev
    Next
    INDEX
    Explanations

    Elden Ring

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    bigvee
    0.39
    लाव
    0.37
    riminate
    0.37
    取り寄せ
    0.36
    老
    0.36
    த்தான்
    0.35
    介绍了
    0.35
    gever
    0.35
     Awareness
    0.35
     replying
    0.35
    POSITIVE LOGITS
    يف
    0.45
     풀
    0.39
    MessageType
    0.39
    фикация
    0.38
    pch
    0.37
    kje
    0.37
     Prost
    0.36
    Fel
    0.36
    ιχ
    0.36
    ኬ
    0.36
    Activations Density 0.018%

    No Known Activations