© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 545
    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
    kę
    2.38
    tedir
    2.29
    ని
    2.27
    घु
    2.08
    ｬ
    2.04
    لي
    1.96
    ambito
    1.95
    amore
    1.94
     kıs
    1.85
     latter
    1.84
    POSITIVE LOGITS
    🅽
    2.19
    й
    1.93
    на
    1.93
    ście
    1.83
    证券投资基金业协会
    1.81
     घिरा
    1.79
     flo
    1.75
     volition
    1.71
    ্বিক
    1.70
     لديك
    1.70
    Activations Density 0.035%

    No Known Activations