© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230430
    Prev
    Next
    INDEX
    Explanations

    MMSE or TSE abbreviations

    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_6_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
    ↵
    1.17
    ER
    0.91
     night
    0.90
     billion
    0.84
     flight
    0.84
     federal
    0.82
    2
    0.82
     festival
    0.79
     day
    0.78
    O
    0.78
    POSITIVE LOGITS
    á
    1.10
    m
    1.07
    r
    0.94
    وم
    0.87
    سوم
    0.85
    re
    0.82
    ى
    0.82
    us
    0.82
    리가
    0.82
    зе
    0.80
    Activations Density 0.001%

    No Known Activations