© 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. 9208
    Prev
    Next
    INDEX
    Explanations

    available / ible / able suffixes

    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
    𝐥
    2.58
    ers
    2.37
    𝐛
    2.34
    aknya
    2.33
     $$\
    2.32
    سلم
    2.29
    са
    2.28
    ed
    2.20
    ̮
    2.17
    
    2.17
    POSITIVE LOGITS
     कराए
    2.82
     iā
    2.79
    ৈধ
    2.54
     chlorine
    2.50
    at
    2.48
     tellement
    2.48
     amin
    2.46
    pedido
    2.41
    ssä
    2.41
    ڈی
    2.40
    Activations Density 0.007%

    No Known Activations