© 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. 9075
    Prev
    Next
    INDEX
    Explanations

    gathers

    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
    בה
    0.92
    м
    0.87
    activiti
    0.87
     Primeiro
    0.85
     Seit
    0.83
    له
    0.83
    مة
    0.82
     quadrants
    0.80
    ا
    0.79
     Liberty
    0.79
    POSITIVE LOGITS
    ر
    1.15
    
    1.06
    𝗻
    1.05
     obvious
    0.93
     dotycz
    0.92
    
    0.90
    
    0.89
    சையில்
    0.88
    ]\\
    0.87
    менно
    0.87
    Activations Density 0.001%

    No Known Activations