© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14622
    Prev
    Next
    INDEX
    Explanations

    code delimiters like 0 ; }

    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
    混ぜ
    0.29
     Mixing
    0.28
     ආරක්ෂ
    0.26
     Motivation
    0.25
     அதிகாரிகள்
    0.25
    跨
    0.25
     Documents
    0.25
     меж
    0.25
     Document
    0.24
    نګ
    0.24
    POSITIVE LOGITS
    Entry
    0.28
    бва
    0.28
     vyš
    0.27
     পাকিস্তানের
    0.27
    €˜
    0.27
    Ez
    0.26
     সপ্তম
    0.26
    媑
    0.26
    дат
    0.25
    လျှ
    0.25
    Activations Density 0.028%

    No Known Activations