© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217698
    Prev
    Next
    INDEX
    Explanations

    biological standpoint

    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_50_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
     perc
    0.55
     Perc
    0.55
    Perc
    0.55
     Pers
    0.54
    pert
    0.52
    Pers
    0.52
     Пер
    0.51
     pere
    0.49
     PER
    0.48
     퍼
    0.46
    POSITIVE LOGITS
    বাল
    0.41
    境界層
    0.36
     ร่วม
    0.36
    過
    0.35
    "،
    0.35
    deel
    0.35
     过
    0.35
    동
    0.35
    Dav
    0.34
    airflow
    0.34
    Activations Density 0.003%

    No Known Activations