© 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. 2088
    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
    ва
    3.06
    de
    2.82
    da
    2.68
    ون
    2.54
    ки
    2.47
    g
    2.43
    ди
    2.41
    или
    2.39
    куда
    2.38
    localObject
    2.38
    POSITIVE LOGITS
    𝗱
    2.99
    𝘀
    2.74
    าค
    2.72
     conjunction
    2.68
    𝗻
    2.63
     danych
    2.57
     postup
    2.50
     اريد
    2.49
     nutshell
    2.47
     dresser
    2.43
    Activations Density 0.197%

    No Known Activations