© 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. 129587
    Prev
    Next
    INDEX
    Explanations

    Birth

    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
    acheal
    0.38
    मानी
    0.38
     ache
    0.35
    멩
    0.35
     Reagan
    0.35
    রাষ্ট্রম
    0.34
    চ্ছু
    0.34
    ::::::::
    0.33
    中最
    0.33
    邾
    0.33
    POSITIVE LOGITS
    ève
    0.45
    neck
    0.42
    فاع
    0.40
    èves
    0.38
     REND
    0.38
    黼
    0.37
     RET
    0.36
    BDF
    0.36
     য
    0.36
    itud
    0.36
    Activations Density 0.001%

    No Known Activations