© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210019
    Prev
    Next
    INDEX
    Explanations

    Director, head, leads, coordinator

    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_19_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
    地域の
    0.51
     planis
    0.48
     resonances
    0.46
     arcu
    0.45
     юбилей
    0.45
    茧
    0.45
    ].”
    0.43
    徇
    0.42
     Arce
    0.42
    lestage
    0.42
    POSITIVE LOGITS
    Employers
    0.43
     зберіга
    0.43
     гля
    0.42
     انتظ
    0.41
     پردا
    0.41
    Powered
    0.41
     emphasises
    0.41
    荅
    0.41
     Positive
    0.40
     дра
    0.40
    Activations Density 0.001%

    No Known Activations