© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24730
    Prev
    Next
    INDEX
    Explanations

    NT AUTHORITY, power brokers

    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_10_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
    做
    0.54
    본
    0.54
    平等
    0.52
    또
    0.51
    Questo
    0.50
    باش
    0.48
    Danh
    0.47
    এ
    0.47
    ET
    0.45
    Además
    0.44
    POSITIVE LOGITS
     demanded
    0.51
     disamb
    0.50
     amplifying
    0.49
    cheng
    0.49
     Acquisition
    0.47
    ata
    0.47
     series
    0.47
     усили
    0.47
     ди
    0.47
    1
    0.47
    Activations Density 0.000%

    No Known Activations