© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167056
    Prev
    Next
    INDEX
    Explanations

    code generation structure

    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_31_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
     Guin
    0.41
     맛
    0.38
     tanda
    0.37
    ätta
    0.37
    ್ಯೂ
    0.37
     系统
    0.36
     Congo
    0.36
     പ്രത്യ
    0.36
    规律
    0.35
     subheading
    0.35
    POSITIVE LOGITS
    ដ្ឋាន
    0.39
    ទ្រ
    0.37
     лето
    0.37
     конфи
    0.36
    ✥
    0.36
     piti
    0.36
    ドル
    0.36
     зарабо
    0.36
    कर्म
    0.35
     gastritis
    0.34
    Activations Density 0.003%

    No Known Activations