© 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. 353
    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
    as
    1.38
    이
    1.29
    ти
    1.12
    了
    1.11
    нды
    1.08
    মাত্র
    0.98
    ส์
    0.96
    יות
    0.95
    ت
    0.94
    IONES
    0.89
    POSITIVE LOGITS
    ا
    1.10
    া
    1.07
     faulted
    1.00
     neckline
    0.99
    cstdio
    0.99
    grimas
    0.97
    요
    0.97
    stdio
    0.96
    Dispose
    0.96
    governmental
    0.93
    Activations Density 0.009%

    No Known Activations