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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260303
    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
    socks
    1.57
    s
    1.51
     hydrophobic
    1.48
    sensors
    1.39
    ریٹر
    1.36
    sounds
    1.31
     APPLY
    1.31
     alleviate
    1.31
    statusbar
    1.28
    QPushButton
    1.27
    POSITIVE LOGITS
    inde
    1.00
    jete
    0.97
    锏
    0.96
    stvo
    0.94
    ived
    0.93
    zel
    0.92
    aksud
    0.92
    ış
    0.92
     referido
    0.92
     тра
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.