Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261899
    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_10_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
    licer
    1.01
    ブーツ
    0.98
    বিষ্ট
    0.98
     Widodo
    0.98
    €™
    0.96
    ाइ
    0.95
    beatable
    0.95
     {-
    0.94
     Chloe
    0.93
    disk
    0.93
    POSITIVE LOGITS
    𝑀
    1.41
    𝐿
    1.32
    𝐺
    1.29
    𝑈
    1.29
    𝑐
    1.29
     rozd
    1.27
    𝑛
    1.26
     gameState
    1.23
    sız
    1.22
    พา
    1.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.