© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52240
    Prev
    Next
    INDEX
    Explanations

    Expenditure, Leave, Magnetic, Information, Transformation, Robotic, Defense, Artificial, Large

    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_30_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
     S
    0.40
     DPRD
    0.39
     Feb
    0.38
     Samen
    0.37
     Baca
    0.37
     RFP
    0.36
     NPs
    0.35
     Ztg
    0.35
     MPs
    0.35
    onomics
    0.34
    POSITIVE LOGITS
     gọi
    0.37
    ▂
    0.36
    ιου
    0.34
     полно
    0.34
    }`}>
    0.33
    жнему
    0.33
    ంగు
    0.33
     folyam
    0.33
    
    0.32
    পিং
    0.32
    Activations Density 0.098%

    No Known Activations