© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200071
    Prev
    Next
    INDEX
    Explanations

    special word or phrase

    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_15_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
     prehistoric
    0.57
     archaic
    0.56
     sanat
    0.54
    ຸ
    0.54
     powerplant
    0.54
    ară
    0.53
     dumpfile
    0.53
     urządzenia
    0.52
    ܠ
    0.52
    راحی
    0.51
    POSITIVE LOGITS
     쌍
    0.46
    所在的
    0.45
    If
    0.44
    En
    0.43
    Customer
    0.41
     huddled
    0.41
    kker
    0.41
    De
    0.40
    vol
    0.39
    Pl
    0.39
    Activations Density 0.000%

    No Known Activations