© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217973
    Prev
    Next
    INDEX
    Explanations

    international organizations

    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_47_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
    U
    0.82
     U
    0.76
    University
    0.67
     u
    0.64
     University
    0.64
     UNIVERSITY
    0.62
    u
    0.55
     यूनिवर्सिटी
    0.54
    UNIVERSITY
    0.54
     یونیورسٹی
    0.53
    POSITIVE LOGITS
     pall
    0.38
     reich
    0.38
    Nonce
    0.37
    ٰذا
    0.37
     Pall
    0.36
    Sue
    0.35
     Ага
    0.35
     appr
    0.35
     ziem
    0.35
    ^_^
    0.35
    Activations Density 0.000%

    No Known Activations