© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1902
    Prev
    Next
    INDEX
    Explanations

    programmed to be a helpful AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    льно
    0.38
     discret
    0.38
    ڵ
    0.38
     Response
    0.38
     Respond
    0.38
     failure
    0.37
    ompact
    0.37
    Responder
    0.36
    ombrie
    0.36
    testng
    0.36
    POSITIVE LOGITS
     SYSTEM
    0.37
    裂
    0.37
    system
    0.37
    hed
    0.36
    跋
    0.36
    Chlor
    0.36
    ەن
    0.35
     systém
    0.35
     मंच
    0.35
     excitatory
    0.35
    Activations Density 0.025%

    No Known Activations