© 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. 217559
    Prev
    Next
    INDEX
    Explanations

    coming

    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
    骚
    0.42
     Conner
    0.40
     Connor
    0.39
    hell
    0.39
     Figaro
    0.39
     boom
    0.38
    नाडु
    0.38
    ધાન
    0.38
    conn
    0.38
    騷
    0.38
    POSITIVE LOGITS
    Beverungen
    0.39
     attainable
    0.38
     терми
    0.37
    морфи
    0.37
    macher
    0.36
    婭
    0.36
     jatuh
    0.36
     भाष
    0.36
    chea
    0.36
     GRID
    0.35
    Activations Density 0.000%

    No Known Activations