© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141806
    Prev
    Next
    INDEX
    Explanations

    Technology leader and driving force

    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_0_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
    ون
    1.08
    ى
    0.97
    у
    0.95
    c
    0.92
    ut
    0.88
    أ
    0.86
    of
    0.84
    ج
    0.81
    り
    0.77
    ق
    0.77
    POSITIVE LOGITS
    มัน
    0.94
    )
    0.79
    ów
    0.75
     exclaimed
    0.72
     momenti
    0.71
     it
    0.71
     chino
    0.70
     habló
    0.67
    dır
    0.65
     maximale
    0.65
    Activations Density 0.000%

    No Known Activations