© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 119416
    Prev
    Next
    INDEX
    Explanations

    Dell Technologies business

    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_38_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
    Њ
    0.47
    Angry
    0.43
     Angry
    0.40
     pens
    0.38
     anger
    0.37
     Anger
    0.37
     hes
    0.37
    恼
    0.37
     industrie
    0.36
     hesitated
    0.36
    POSITIVE LOGITS
    uart
    0.43
    小组
    0.38
     Worlds
    0.38
     сере
    0.37
    édération
    0.37
     Shreve
    0.36
    PARA
    0.36
    Witt
    0.35
     World
    0.35
    Tables
    0.35
    Activations Density 0.020%

    No Known Activations