© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54561
    Prev
    Next
    INDEX
    Explanations

    for technical specifications and purpose

    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_30_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
     Amid
    0.39
     midst
    0.38
     amidst
    0.35
     devoting
    0.34
     persuade
    0.33
     amid
    0.32
     வளர்ச்ச
    0.32
    ນ
    0.32
     Alto
    0.32
     nailed
    0.32
    POSITIVE LOGITS
     для
    0.98
     untuk
    0.93
     για
    0.91
     pentru
    0.90
    សម្រាប់ការ
    0.89
     für
    0.88
    สำหรับการ
    0.88
     برای
    0.84
     kanggo
    0.84
    untuk
    0.82
    Activations Density 0.059%

    No Known Activations