© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8972
    Prev
    Next
    INDEX
    Explanations

    multilingual word fragments

    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
    Negative Logits
    st
    2.21
    ss
    2.14
    ஸ்
    2.06
    tt
    2.05
    ється
    2.00
     třeba
    1.97
    gne
    1.94
    tts
    1.93
    fulness
    1.92
    𝑉
    1.90
    POSITIVE LOGITS
    ের
    2.72
    ς
    2.65
    ์
    2.65
    ма
    2.58
    ystem
    2.42
    ים
    2.40
    ми
    2.37
     مختلف
    2.33
    වල
    2.27
    ات
    2.22
    Activations Density 0.005%

    No Known Activations