© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202171
    Prev
    Next
    INDEX
    Explanations

    mutually exclusive

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consent
    0.41
     Произ
    0.40
     reread
    0.39
     words
    0.39
     Horizontal
    0.38
     agree
    0.37
     భ
    0.37
     "***
    0.37
     Production
    0.37
     خاطر
    0.37
    POSITIVE LOGITS
     एकमे
    0.45
    Each
    0.44
    AspNetUser
    0.41
     comunicación
    0.40
    ურთიერთ
    0.39
    lasts
    0.38
     প্রতিভা
    0.38
     komunikasi
    0.38
    แต่ละ
    0.38
    ждая
    0.38
    Activations Density 0.001%

    No Known Activations