© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8644
    Prev
    Next
    INDEX
    Explanations

    28x28 dimensions

    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_3_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
    manship
    2.51
    Slf
    2.38
    ◾
    2.32
     masu
    2.29
     rheumatic
    2.28
    poj
    2.22
    ع
    2.20
    ոչ
    2.18
    ी
    2.13
    
    2.12
    POSITIVE LOGITS
    р
    2.50
     أجل
    2.45
    ה
    2.44
    ्रल
    2.43
    いる
    2.26
    یل
    2.23
    ণ
    2.11
    a
    2.10
    ্স
    2.10
    ртов
    2.03
    Activations Density 0.040%

    No Known Activations