© 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. 3683
    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
    rocket
    1.68
    Guitar
    1.58
    ि
    1.55
    updateOne
    1.53
     diat
    1.53
    ंगाबाद
    1.49
    ি
    1.44
    """"""""
    1.44
    arrow
    1.42
    δι
    1.41
    POSITIVE LOGITS
    ENING
    1.66
     Veneto
    1.54
     augmente
    1.50
     массы
    1.49
     sonucu
    1.46
     অবস্থায়
    1.46
     விழுப்புரம்
    1.46
    le
    1.46
    ндә
    1.44
    壑
    1.43
    Activations Density 0.013%

    No Known Activations