© 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. 9219
    Prev
    Next
    INDEX
    Explanations

    rosewood hotels

    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
    ти
    2.09
    ள்ளது
    1.69
    ي
    1.69
    ط
    1.52
    arono
    1.47
    в
    1.47
    ر
    1.45
     Grâce
    1.45
     Более
    1.43
     chien
    1.42
    POSITIVE LOGITS
    n
    1.64
     tand
    1.55
    nur
    1.50
    м
    1.50
    ьи
    1.47
    jší
    1.45
     clínico
    1.44
     Heisenberg
    1.41
    िया
    1.39
    ตรฐาน
    1.35
    Activations Density 0.002%

    No Known Activations