© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34091
    Prev
    Next
    INDEX
    Explanations

    financial and political

    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
     De
    0.46
    De
    0.43
     де
    0.41
     SHA
    0.40
    デ
    0.39
     Де
    0.39
     XV
    0.38
    Де
    0.38
     britt
    0.38
     Deccan
    0.38
    POSITIVE LOGITS
     sop
    0.46
     সো
    0.46
     Sop
    0.43
    sop
    0.40
    coding
    0.39
    Sol
    0.39
     တို့
    0.38
    łop
    0.38
     socket
    0.37
    織
    0.37
    Activations Density 0.018%

    No Known Activations