© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15291
    Prev
    Next
    INDEX
    Explanations

    educational assessments and exams

    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_13_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
    zo
    0.51
    と思いますが
    0.49
    స్ట్
    0.46
    дой
    0.45
    ัว
    0.44
    但在
    0.44
    מה
    0.43
     unamb
    0.42
    Ari
    0.42
     \%$
    0.42
    POSITIVE LOGITS
     Exams
    0.55
     siswa
    0.52
     Pupils
    0.52
     pupils
    0.51
     Jugendlichen
    0.49
     Academy
    0.48
     Teens
    0.47
     skepticism
    0.47
     Defenders
    0.46
     teenagers
    0.45
    Activations Density 0.006%

    No Known Activations