© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 209967
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
    лу
    0.35
     Wikiseite
    0.35
    myn
    0.35
    対象
    0.33
     ভঙ্গ
    0.33
    ться
    0.32
    їн
    0.32
    ҥ
    0.32
     სა
    0.32
     шту
    0.32
    POSITIVE LOGITS
    Each
    0.48
     Each
    0.45
     each
    0.42
     Maurer
    0.41
    IsNull
    0.40
    Maur
    0.40
     mỗi
    0.40
    Suzanne
    0.40
     Liss
    0.39
    Truman
    0.39
    Activations Density 0.001%

    No Known Activations