© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2301
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ことになる
    3.20
    ة
    2.84
    на
    2.84
     pulgadas
    2.60
    ε
    2.60
    こと
    2.58
    вичай
    2.57
    ת
    2.47
     steigt
    2.46
    ையுடன்
    2.45
    POSITIVE LOGITS
    м
    3.19
    
    2.97
    д
    2.77
     clapping
    2.76
    
    2.74
     soiled
    2.62
    ributions
    2.57
     pounding
    2.55
    ्राट
    2.51
    з
    2.43
    Activations Density 0.011%

    No Known Activations