© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9905
    Prev
    Next
    INDEX
    Explanations

    early history

    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_40_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
     metam
    0.41
     immers
    0.38
     NEM
    0.37
     पंडित
    0.35
    வர்களில்
    0.35
    웜
    0.35
     higiene
    0.35
    媝
    0.35
    ☬
    0.35
     охра
    0.34
    POSITIVE LOGITS
    ındaki
    0.38
    useum
    0.37
     Hàm
    0.37
     invading
    0.36
    ributive
    0.36
    Nieder
    0.35
    ೫
    0.35
     formée
    0.34
     yt
    0.34
    ตร์
    0.34
    Activations Density 0.044%

    No Known Activations