© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130024
    Prev
    Next
    INDEX
    Explanations

    sci / scrapy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     النهايات
    0.42
    범
    0.40
    Roh
    0.40
     AVERAGE
    0.38
     Roh
    0.38
    𝙾
    0.38
     Average
    0.37
    卒
    0.37
    Weapon
    0.37
     बोल
    0.36
    POSITIVE LOGITS
    церт
    0.42
    aint
    0.42
    arto
    0.38
     аккумулятор
    0.38
    йн
    0.38
    ART
    0.37
     Cass
    0.37
    月に
    0.37
    اصر
    0.37
    argy
    0.37
    Activations Density 0.002%

    No Known Activations