© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3101
    Prev
    Next
    INDEX
    Explanations

    how to say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    le
    3.87
    ا
    3.16
    특별시
    3.14
    د
    3.13
    Trajectory
    3.12
    siniz
    3.00
    ers
    3.00
    ेक्स
    2.96
    
    2.92
    delt
    2.91
    POSITIVE LOGITS
     thereto
    3.30
    ات
    3.16
     إليه
    3.14
     إليها
    2.91
    限于
    2.88
     solutes
    2.77
    가
    2.65
    না
    2.62
     thờ
    2.59
    পরে
    2.57
    Activations Density 0.877%

    No Known Activations