© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201720
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    س
    1.52
    ن
    1.43
    ু
    1.32
     a
    1.27
     to
    1.23
    ir
    1.23
    ल
    1.21
    น
    1.19
    ม
    1.19
    ס
    1.15
    POSITIVE LOGITS
    стави
    0.88
    t
    0.87
    OR
    0.81
    ation
    0.80
     الاجتماعي
    0.80
    ಕ್ಕಾಗಿ
    0.79
     Цент
    0.77
    кмекер
    0.76
     গ্রন্থ
    0.76
     фаразлары
    0.74
    Activations Density 0.000%

    No Known Activations