© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16343
    Prev
    Next
    INDEX
    Explanations

    **starred items**

    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_34_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
    শালী
    0.40
     "@
    0.39
     herringbone
    0.39
     विरु
    0.39
     terbatas
    0.38
    Friendly
    0.37
     angrily
    0.37
    Possible
    0.37
     `@
    0.37
    ूले
    0.37
    POSITIVE LOGITS
     officials
    0.44
     preocup
    0.40
     راز
    0.40
    驿
    0.40
     الي
    0.38
    isol
    0.37
     clin
    0.37
     Wor
    0.37
    wor
    0.37
     Sinh
    0.37
    Activations Density 0.006%

    No Known Activations