© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167837
    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_56_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
    自
    0.48
    对
    0.45
     tự
    0.44
     self
    0.43
    会对
    0.42
    對
    0.40
    غه
    0.39
    Receive
    0.38
     ricev
    0.37
    self
    0.36
    POSITIVE LOGITS
     khá
    0.62
     bastante
    0.54
     assez
    0.52
     nokt
    0.48
     abbastanza
    0.46
     proj
    0.45
     точка
    0.45
     точки
    0.45
     đ
    0.44
     काफी
    0.43
    Activations Density 0.000%

    No Known Activations