© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35086
    Prev
    Next
    INDEX
    Explanations

    programmed to be helpful

    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
     مقاوم
    0.40
    ሃኒ
    0.38
    的点
    0.38
    করণ
    0.38
     ober
    0.37
    偖
    0.37
     نقطه
    0.37
    敺
    0.36
     धर्मेंद्र
    0.36
    নাট
    0.36
    POSITIVE LOGITS
     Саме
    0.42
    olia
    0.38
     permitido
    0.38
    etil
    0.36
     процент
    0.36
    olla
    0.35
    raf
    0.34
     transm
    0.34
     piss
    0.33
    BDF
    0.33
    Activations Density 0.025%

    No Known Activations