© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148721
    Prev
    Next
    INDEX
    Explanations

    screen setup in python turtle

    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_23_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
    ﹒
    0.45
     मसा
    0.42
    sime
    0.41
    ContextProvider
    0.40
     чувства
    0.40
    कृ
    0.39
    гона
    0.38
    pozy
    0.38
    }[[
    0.38
     ид
    0.38
    POSITIVE LOGITS
     స్థాప
    0.42
    参数向量
    0.38
    lungen
    0.38
     radiometric
    0.38
    険
    0.38
     erro
    0.38
     debated
    0.38
     ইস্যুতে
    0.38
    ਡੀ
    0.37
     парамет
    0.37
    Activations Density 0.001%

    No Known Activations