© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223681
    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_10_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
     الصحة
    0.51
    ↵↵
    0.48
    Trad
    0.46
    Sergio
    0.45
     الآ
    0.44
    com
    0.43
    ల్
    0.43
    Mal
    0.43
     كوم
    0.43
     continuo
    0.43
    POSITIVE LOGITS
     purposely
    0.51
     metallic
    0.50
     ?>">
    0.49
     geldiniz
    0.49
     کری
    0.48
    idcoin
    0.47
     dépassant
    0.47
    کری
    0.46
     epoxide
    0.46
     realizzazione
    0.45
    Activations Density 0.000%

    No Known Activations