© 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. 260924
    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
    샛
    1.50
     jeweiligen
    1.41
    ت
    1.39
    ⿶
    1.33
     unge
    1.31
    İ
    1.30
     variabili
    1.27
     ime
    1.26
    िवा
    1.25
     なお
    1.24
    POSITIVE LOGITS
    othesis
    0.95
    atenate
    0.89
     छ
    0.87
    ണ്ടും
    0.87
    ously
    0.86
    cosh
    0.86
     ملت
    0.86
    ヒット
    0.85
    canny
    0.85
    ども
    0.85
    Activations Density 0.000%

    No Known Activations