© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4852
    Prev
    Next
    INDEX
    Explanations

    gel or jelly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_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
    ీ
    2.04
    ீ
    2.00
    urile
    1.97
    urilor
    1.91
    té
    1.88
    िता
    1.88
    ক
    1.86
    лле
    1.82
     fim
    1.81
    ка
    1.81
    POSITIVE LOGITS
     Qxd
    2.29
    aní
    2.10
     electrophoresis
    1.97
     nutritious
    1.96
    👉
    1.94
    arXiv
    1.93
    an
    1.91
    ד
    1.86
     moguće
    1.81
    mailing
    1.81
    Activations Density 0.009%

    No Known Activations