© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2029
    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
     latitudes
    2.42
     thermostats
    2.30
    ted
    2.25
     rétrécies
    2.24
     SNPs
    2.17
    ⿷
    2.16
    री
    2.15
    ຕ້ອງ
    2.13
     Nullam
    2.07
    cemia
    2.06
    POSITIVE LOGITS
    ει
    2.22
     таки
    2.16
     immobilier
    2.06
    ساس
    2.01
    ../../
    1.98
    dg
    1.97
     cé
    1.90
    д
    1.87
    ্ড
    1.86
    ...+
    1.86
    Activations Density 0.016%

    No Known Activations